OpenClaw is a security nightmare dressed up as a daydream

https://composio.dev/content/openclaw-security-and-vulnerabilities

by fs_software • 4 months ago

397 287 4 months ago

airstrike• 4 months ago

I wonder just how many are compromised and waiting on a command that hasn't been given yet

All of them. It's not like AI companies have managed to fix the security issues since last time they promised they had fixed all the hallucinations & accidental database deletions.

gos95• 4 months ago

You know it’s open source code, right?

vessenes2• 4 months ago

Yes, yes it is. And it's amaaaazing. We're going to have lots of sharp edges getting stuff like this secured, but it is not going to go away. Too useful.

plufz• 4 months ago

Can you tell me about your favorite use cases?

mstkllah• 4 months ago

What are your uses for it? If you don't mind sharing.

quietsegfault• 4 months ago

I haven’t found ANY uses for it where it actually did what it was supposed to do.

pupppet• 4 months ago

I wonder about this as well. I see people breathlessly talking about how it manages their inbox or checks flight statuses, but how often should you need a bot for these things?

sodapopcan2• 4 months ago

Writing blog posts and HN comments about how awesome OpenClaw is its #1 utility.

phil21• 4 months ago

For me, personal home IT “chores” that I’ve put off for years. I can do them, but god what a pain in the ass to spin up a VM, configure Prometheus, configure grafana, configure a bunch of collectors for my WiFi and network infrastructure, and then spend a night or three tweaking dashboards and re-learning promql or whatever.

I just end up never doing it. Got it done in a couple hours with openclaw.

I’m sure there are much better ways to do that, which I will now learn in time due to the initial activation energy being broken on the topic. But for now, it’s fun running down my half decade old todo list.

simonw3• 4 months ago

The first company to deliver a truly secure Claw is going to make millions of dollars.

I have no idea how anyone is going to do that.

_pdp_4• 4 months ago

There are secure alternatives but they are not making millions of dollars.

ares623• 4 months ago

That's easy. We just keep pumping these things and remind everyone that there's no real consequences (at least to the people who actually matter) and what was previously agreed as super important and critical will eventually turn out to no longer be super important or critical. Lethal trifecta solved. Who cares if your agent is forwarding private and confidential emails to random people, if everyone else is doing it too. Syndrome from the Incredibles movie won, and we helped make it happen. In fact, we made sure of it.

deaux• 4 months ago

The same way as delivering a "truly secure human". Which is of course impossible, that's why spies, double agents and even triple agents exist and have succeeded to do their job. And that's despite an enormous number of guardrails meant to prevent exactly that.

And simply "secure enough" doesn't help much either, because whereas a single human spy can only do so much damage, if an LLM is given access to everything in one way or another - which is the whole concept - then the potential damage is boundless.

vessenes2• 4 months ago

It seems almost impossible. I spent the weekend comparing nanoclaw to openclaw - nanoclaw is a slightly more secure version - containerized filesystem basically - and very popular.

It's a) harder to setup, b) less functional out of the box, c) has almost exactly the same security risk surface -- either you hook it up to your email, comms, documents and give it API tokens, or you don't. If you do -- well, at least it can't delete your hard drive without turning full evil and looking for red pill type exploits that break the container -- but, it still has the same other security dynamics.

Anyway, employing a very suspicious watcher that's hooked to the shell and API calls is probably the way forward. Can that thing be reasoned with / tricked?

user3939382• 4 months ago

You assume the security is something you bolt on rather than the security weakness being inextricable from the value. The superior approach is to distill what the LLM is doing, with careful human review, into a deterministic tool. That takes actual engineering chops. There’s no free lunch.

somewhereoutth2• 4 months ago

I would like a personal assistant on my phone that, based on my usual routine and my exact position, can tell me (for example) which bus will get me home the quickest off the ferry, whether the bridge is clogged with traffic, do I need an umbrella? what's probably missing from my fridge, time to top up transit pass, did I tap in? etc etc. These things would appear on my lock screen when I most probably need to know them.

No email stuff, no booking things, no security problems.

cj• 4 months ago

I mean that also sounds like a logical first step.

If “AI” can predict what you need, start with that. And layer in the “do it for me” (“book me the 1pm ferry”) later on.

Angostura• 4 months ago

Sounds like you just need to install Apple Maps, Apple Weather^* and some separte fridge-tracking app. No need of additional intrusive AI

^* or equivalents

somewhereoutth2• 4 months ago

Indeed I have a bunch of apps that do most of these things, but it's the seamless integration I'm looking for - which may not need much AI at all (especially of the LLM kind), just some well directed machine learning and UI integration.

esskay• 4 months ago

In an alternative reality Apple didn't absolutely shit the bed on AI and made this possible. Sadly they've shown they are woefully behind and have utterly useless people leading divisions they shouldn't have been allowed anywhere near.

gos95• 4 months ago

No security problems carries a lot of weight here because by design you’re having to expose a significant amount of information but this is doable as a weekend project

feznyng2• 4 months ago

How? There's a bunch of annoying problems here:

- Where do you source real time traffic data, ferry schedules, etc? Google APIs get you part of the way there but you'd need to crawl public transit sites for the rest.

- How do you keep track of what went into the fridge, what was consumed/thrown away?

- How do you track real world events like buying a physical pass?

Ekaros• 4 months ago

Sounds like there is need for decent singular interface for bunch of expert systems. Sadly I think everyone is so deep into locking their own thing down from others that this will never happen.

rickdg• 4 months ago

Oarch3• 4 months ago

Responding to the tweet quoted in the article: why are the examples given of futuristic capabilities always so visionless - it's always booking a flight or scheduling a meeting. Doing this manually is already pretty trivial, it's more productivity theatre than genuinely life-changing.

There are real, impressive examples of the power of agentic flows out there. Can we up the quality of our examples just a bit?

AlienRobot3• 4 months ago

For example?

Oarch3• 4 months ago

It would probably depend on the target audience.

I was very impressed by Anthropic's swarm of agents building a C compiler earlier this year with 1000 PRs per hour. Easy to nitpick that it wasn't perfect, but it sure was impressive.

refulgentis3• 4 months ago

Can we up the quality of our examples just a bit?

No.

And there’s mundane answers why.

People used to talk about phone home screens, back in the day, every iPhone had 16 spots

It became wisdom everyone had the same 12 apps but then there were 4 that that were core for you and where most of your use went, but they were different apps from everyone else.

So it goes for agent demos.

Another reason: every agentic flow is a series of mundane steps that can be rounded to mundane and easy to do yourself. Value depends on how often you have to repeat them. If I have to book a flight once every year, I don’t need it and it’s mundane.

There’s no life changing demo out there that someone won’t reply dismissively to. If there was, you’d see them somewhere, no? It’s been years of LLMs now.

Put most bluntly: when faced with a contradiction, first, check your premises. The contradiction here being, everyone else doesn’t understand their agent demos are boring and if just one person finally put a little work and imagination into it, they’d be life changing.

otabdeveloper42• 4 months ago

There are easy no-brainer productivity boosts with LLMs. For example, automatically sorting your email by topic.

Nobody shows this because the technology is still immature and very shit.

usui• 4 months ago

Have you seen how bad flight booking sites can get? I've had to download airline apps a majority of the time because the website failed to finish payment properly.

I don't think we should call presentations visionless or fault them for wanting to solve this UX nightmare.

thinkingtoilet• 4 months ago

That is never happened to me once.

gum_wobble• 4 months ago

So the solution to bad design and enshittification is to have an horde of agents to throw at tasks now?

dawnerd2• 4 months ago

And this sounds like something you absolutely wouldn’t want an ai agent trying to figure out.

amanzi• 4 months ago

And you want to add an unreliable, non-deterministic LLM into the flow too?

ceejayoz• 4 months ago

Have you seen how bad flight booking sites can get?

Claude is pretty amazing, but it still goes down rabbit holes and makes obvious mistakes. Combining that with "oops I just bought a non-refundable flight to the wrong city" seems... unfun.

ForHackernews• 4 months ago

The dream of the middle class IT drone is to become the executive Office Man: he shouts at his PA and she books his flights.

Now AI can provide a simulacrum of his fondest aspiration, to be too important to click through booking.com and make someone else do it for him.

kbenson• 4 months ago

Well, I've taken to describing the best responsible use of AI to help your work as though you have an executive assistant, so I can see why people would come to that conclusion. I don't tend to think of booking flights for that though, I tend to think of asking them to gather information and present it to me so I can review it for whether it's appropriate to include, probably with changes, in whatever I'm working on. Perhaps an executive assistant isn't the right term for that, or perhaps it's just that different people and different industries have vastly different ideas of how to make use of an executive assistant. I don't know enough to answer that.

bitwize2• 4 months ago

Been a middle-class IT drone much of my adult life. This is not my dream. In fact I just realized that one reason I don't like AI dev tools is because they turn me into the kind of dickhead manager I despise: one who doesn't understand the code or the nature of the work involved, just gives orders on what needs to be built and complains when it doesn't work.

sdoering• 4 months ago

Not using OpenClaw - but I have a limited agent running that currently does a few things well.

Morning Briefing: - it reads all my new email (multiple accounts and contexts), calendars (same accounts and contexts), slack (and other chat) messages (multiple slacks, matrix, discord, and so on), the weather reports, my open/closed recent to dos in a shared list across all my devices, my latest journal/log entries of things done. Has access for cross referencing to my "people files" to get context on mails/appointments and chat messages.

From all this, as well as my RSS feeds, it generates a comprehensive yet short-ish morning briefing I receive on weekdays at 7am.

Two minutes and I have a good grasp of my day, important meetings/deadlines/to dos, possible scheduling conflicts across the multiple calendars (that are not syncable due to corporate policies). This is a very high level overview that already enables me to plan my day better, reschedule things if necessary. And start the day focused on my most important open tasks/topics. More often than not this enables me to keep the laptop closed and do the conceptual work first without getting sucked into email. Or teams.

By the way: Sadly teams is not accessible to it right now. MS Power Automate sadly does not enable forwarding the content of chats. Unlike with emails or calendar appointments.

Just for that alone it is worth having it to me. YMMV.

I also can fire a research request via chat. It does that and writes the results into a file that gets synced to my other devices. Meaning I have it available at any device within a minute or so. Really handy sometimes. It also runs a few regular research tasks on a schedule. And a bit of prep work for copy writing and stuff like this.

Currently it is just a hobby/play project. But the morning briefing to me is easily worth an hour of my day. Totally worth running it on my infra without additional costs.

aftbit2• 4 months ago

possible scheduling conflicts across the multiple calendars (that are not syncable due to corporate policies)

Doesn't this sorta defeat those policies though? Now all of your calendars are "synced" to a random unvalidated AI agent.

vl• 4 months ago

What are you using for email integration?

I want to setup agent to clean up my gmail inbox which has many thousands of unread messages.

Atiscant• 4 months ago

Would you mind adding some details about how this is actually setup?

PurpleRamen• 4 months ago

Morning Briefing

How do you ensure that it's not hallucinating stuff, or ignoring something important?

Terretta• 4 months ago

Sadly teams is not accessible to it right now. MS Power Automate sadly does not enable forwarding the content of chats. Unlike with emails or calendar appointments.

In the spirit of CLIs being easy on your tokens:

https://pnp.github.io/cli-microsoft365/cmd/teams/chat/chat-g...

Use the JSON responses for full detail including e.g. reactions.

Composio, behind the blog post, offers "Enterprise" pricing, and has no Teams examples. A stat HN ignores: 85% of SMBs are on M365, not Google Workspace and Slack.

You can pick winners and losers in a segment early, by whether they treat M365 as a first class platform or pretend it doesn't exist. Check for the "Continue with Microsoft" button or support for OIDC not just SAML+SCIM, as well as examples for Teams.

This isn't just true for YC classes, holds true for unicorns. Compare Anthropic's "Claude in Excel" and "Claude in PowerPoint" instead of in Google Docs or Sheets, and guess which firm has a better grasp of how business works outside the valley. And yeah, Claude in Chrome works in Edge (and the lack of just renaming and posting Claude in Edge for normals to find is an ANTHROP\C miss).

bluGill• 4 months ago

They are only trivial in the simple case.

When you need a bunch of busy people in a meeting it becomes hard to book a meeting. If several people need to travel incuding get a visa it is hard to fit it all it between other meetings that refuired people caanot skip.

travel is hard when you are trying for the best deal across flights, hotels and such. many sites only guarentee prices for 15 minutes so you can't even get all the needed prices on a spreadsheet at once - particularly if you have flevible travel dates. I've booked a best price plane ticket only to discover it was the worst date for hotels and I could have saved money on a more expensive flight.

mjr002• 4 months ago

why are the examples given of futuristic capabilities always so visionless - it's always booking a flight or scheduling a meeting.

This AI wave is filled with "ideas guys/gals" who thought they had an amazing awesome idea and if only they knew how to program they could make a best-selling billion dollar idea, being confronted with the reality that their ideas are really uninteresting as well.

They're still happy to write blog posts about how their bleeding-edge Claw setup sends them a push notification whenever someone comments on one of their LinkedIn posts, though.

stbtrax• 4 months ago

the whole obsequious nature of how LLMs also amp them up thinking they're onto something incredible is throwing gas on this dumpster fire.

"What a great idea! This will revolutionize linkedin commenting. Let's implement it together."

brightball• 4 months ago

Wait til you see my todo app though…

_dain_• 4 months ago

Yeah it seems like we're still in the "XYZ ... but on a computer!" stage of AI.

FpUser2• 4 months ago

I have "new genius" ideas very often. After doing quick search I discover that any idea worth thinking of implementation is either implemented already or what seems to be low barrier to entry clashes with some legal obstacles.

Barrin92• 4 months ago

There are real, impressive examples of the power of agentic flows

there aren't, and just like the blockchain "industry" with its "surely this is going to be the killer app" we're going to be in this circus until the money dries up.

Just like the note-taking craze, the crypto ecosystem and now AI there's an almost inverse relation between the people advocating it and actually doing any meaningful work. The more anyone's pushing it the faster you should run into the opposite direction.

aftbit2• 4 months ago

I'm gonna keep saying this forever - there are two obvious "killer apps" for crypto:

1. Semi-private blockchains, where you can rely on an actor not to be actively malicious, but still want to be able to cryptographically hold them to a past statement (think banks settling up with each other)

2. NFTs for tracking physical products through a logistics supply chain. Every time a container moves from one node to the next in a physical logistics chain (which includes tons of low trust "last mile" carriers), its corresponding NFT changes ownership as well. This could become as granular as there's money to support.

These would both provide material advantages above and beyond a centralized SQL database as there's no obvious central party that is trusted enough to operate that database. Neither has anything to do with retail investors or JPEGs though, so they'll never moon and you'll never hear about them.

sxg• 4 months ago

Some of it is lack of imagination, but some of it is because many truly visionary examples would largely sound stupid to most of today's audience. Imagine it's 2007 and you're explaining how the smartphone will change society over the next 20 years:

- A photo sharing app will change restaurants, public spaces, and the entire travel industry across the world

- The smartphone will bring about regime change in Egypt, Tunisia, Lebanon, and other countries in ~4 years

- We'll replace taxis and hotels by getting rides and sharing homes with strangers

- Billions of people across the world will never need to own a desktop or laptop

- A short video sharing app will kill TV

- QR codes become relevant

Most of these would be a hard sell at the time.

namibj• 4 months ago

Instagram Arabian spring Uber Airbnb Cloud-ification/shift to web apps and mobile-first ....tiktok? Or is YouTube considered "short video sharing app"? Because I see no evidence tiktok in particular killing TV... To be fair, QR code did hit print magazines/newspapers in Germany (just as an example; English wiki was not elaborating on initial history of public use/perception) in late 2007, so that one wasn't nearly as far-fetched.

runarberg5• 4 months ago

None of these actually were hard to sell. In 2007 we had mobile phones, we had mp3 players (the iPod was actually very good), we had CouchSurfing, etc.

I think the smart phone revolution is actually pretty overstated. It basically only made computers cheaper and handier to carry (but also more walled gardens). There are a few capabilities of smart phones we do today which we didn’t with do with computers and mobile phones back in 2007, such as navigation (GPS were a thing but not used much by the general public).

Your case would be much stronger if you’d use the World Wide Web as your analogy, as in 1995 it would by hard to convince anybody how important it would be to maintain a web presence. And nobody would guess a social media like the irc would blow up into something other then a toy.

However I think the analogy with smartphones are actually more apt, this AI revolution has made statistical models more accessible, but we are only using them for things we were already capable of before, and unlike the web, and much like smartphones, I don’t think that will actually change. But unlike smartphones, it will always be cheaper and often even easier to use the alternatives.

adrianwaj• 4 months ago

- A nation-agnostic online currency (and its offshoots) would lead to a multi-polar world.

- Publicly waving your resume around will passively invite job interviews.

There's a new OpenClaw adaptation, Ottie, that I think could be a bank manager, bank teller, stockbroker, piggy bank, accountant, wallet, security guard and credit card provider all rolled into one. I just haven't used it yet. https://ottie.xyz/

So that would be:

- Digital sidekick weeds out parasitic relationships.

There has to be tremendous value in that.

When solutions are looking for problems, it means that things may seem oversold when in fact they are still undersold.

sylos• 4 months ago

I think some folks want a legitmate personal assistant/secretary like ceo's and wealthy people have but ai. I think that's a good goal. Modern cells and pdas kinda fell short of "your own literal secretary" and I think people want that. Still we should continue pushing the boundaries beyond that.

the_snooze2• 4 months ago

The purpose of a personal assistant isn’t to fit people into your calendar. It’s to filter them out. They serve as a barrier to your time, not an enabler for other people to claim it. I don’t see how an AI can meaningfully accomplish that any better than simply just making yourself more difficult to reach.

array_key_first3• 4 months ago

They really didn't fall short. A lot of people who would've had assistants no longer do, now it's really just the executives like you said. But fairly low managers used to have them and now they don't.

Software is pretty good. It remembers everything, perfectly, forever. It will never forget to remind you of something. It can give you directions, sort your emails by how important they are, help you find shops and restaurants. The only people busy enough to warrant an actual human doing that stuff are executives. And, even then, I think for most of them it's an ego thing, not an "I need this" thing.

endofreach• 4 months ago

There are real, impressive examples of the power of agentic flows out there. Can we up the quality of our examples just a bit?

Please don't. The reason we're still enjoying the bit of the old world as we know it, is just because nobody has really figured it out yet. Enjoy the moment, while it lasts.

enraged_camel2• 4 months ago

What does this even mean? By definition, we have been enjoying "the moment" for quite a while now. What is so special about it that we should work to prolong it, and to avoid moving forward?

ljm• 4 months ago

The real impressive examples get turned into SaaS prototypes and not placeholders for your imagination.

If they had vision they wouldn't be thrown out in a blog post.

timacles• 4 months ago

This is the tech equivalent of my girlfriend goes to another school.

If someone implemented something impressive with this stuff, they wouldnt be keeping it quiet. False negatives are unproductive

brotchie• 4 months ago

OpenClaw is just like any other tool, you need to learn it before its power is available to you.

Just like anything in engineering really: you have to play around source control to understand source control, you have to play around with database indexes to learn how to optimize a database.

Once you've learned it and incorporated it into your tool set, you then have that to wield in solving problems "oh, damn, a database index is perfect for this."

To this end, folks doing flights and scheduling meetings using OpenClaw are really in that exploration / learning phase. They tackle the first (possibly uninventive thing) that comes to mind to just dive in and learn.

The real wins come down the line when you're tackling some business / personal life problem and go: "wait a second, an OpenClaw agent would be perfect for this!"

imiric• 4 months ago

OpenClaw is just like any other tool, you need to learn it before its power is available to you.

That's ridiculous. The utility of any tool is usually knowable before using it. That's how most tools work. I don't need to learn how to drive a car to know what I could use it for. I learn to drive it because I want to benefit from it, not the other way around.

It's the same with computers and any program. I use it to accomplish a specific task, not to discover the tasks it could be useful for.

OpenClaw is yet another tool in search of a problem, like most of the "AI" ecosystem. When the bubble bursts, nobody will remember these tools, and we'll be able to focus on technology that solves problems people actually have.

phist_mcgee• 4 months ago

The real wins come down the line when you're tackling some business / personal life problem and go: "wait a second, an OpenClaw agent would be perfect for this!"

Such as?

lxgr4• 4 months ago

That's a fair point, and I guess the marketing problem here is intrinsic: If the problem is trivial, off-the-shelf solutions abound; if it's idiosyncratic, almost nobody will be able to relate (as you can't assume that people will do the transfer of "if it can solve complex problem I don't understand A, it'll probably be able to solve my complex problem B" for promotional material).

davidw2• 4 months ago

Booking a flight is the kind of thing I want to dedicate my full attention to. It's expensive, and the timing and details matter a lot.

I'm happy for the voice assistant to add stuff to my grocery list, though. The consequences are not serious if it screws up a letter or something.

etiam• 4 months ago

Booking a flight is the kind of thing I'd really want to avoid doing myself nowadays if possible though. Surveying the offers is usually such a snake pit of deceptive marketing and incomplete service conditions that I feel somewhat nauseous just at the prospect of having to look at it.

I wouldn't remotely trust a software assistant to deal with all that misdirection autonomously, but I guess I'd be prepared to give it a chance collating options with tolerable time and cost, attempting to make the price include the stuff that has to be added to preserve health, sanity and a modicum of human dignity.

Ferret7446• 4 months ago

We will get to the point where you'll trust it to catch those issues. The latest models can already do it sometimes for code, like explain that it considered various options and the tradeoffs between them.

ericd8• 4 months ago

Apparently I'm the only one here who finds it to be one of the worst things I ever have to do, I hate managing the combinatorial tab explosion by hand. Compounded by the adversarial nature of the price-setting algorithms that jack up the price on you if you show too much interest by researching too intensively. Just booked a flight for our family in two parts, and booking for one set of us made the price for the second set of us with a slightly different itinerary massively more expensive, because it was "in demand".

Can't wait for agents to handle all of it.

viccis• 4 months ago

Exactly. When you're spending money, you want to be in the loop. It's why the Alexa Echo devices as media for Amazon purchases never really worked out. Amazon had two conflicting aims. They wanted to race to the bottom with their increasingly shady vendors which eroded trust, while also positioning themselves and their devices to be trusted agents of purchases. Of course no one wants to buy anything sight unseen through them.

kelnos7• 4 months ago

To be fair, you can cancel flight reservations for a full refund within 24 hours, so if the LLM gets it wrong, you're not on the hook for anything.

But in general I do agree: flight bookings are something I want to do myself, because even I don't fully know my preferences when it comes to timing and price until I see what's available. And in general I don't find it all that difficult to do. A couple days ago I booked a multi-city travel itinerary with four different destinations, and it took me about a half hour?

Sure, if an LLM can do that in under a minute, that would be cool, but in absolutely zero situations would I not need to check its work, and if it did get it wrong, I'd have to do it all myself anyway.

takinola2• 4 months ago

Booking a flight is the type of thing you think you want to dedicate your full attention to. Largely, the issue is one of trust that whatever is making the bookings will take into account the nuances of your schedule and preferences. Here's the typical flow for how my (human) assistant books my flights. I tell them I want to go to $LOCATION from $START to $END. They have my calendar, my travel preferences (airlines, hotels, etc) and the company travel policy. A couple hours later, they slack me a couple of options. If there is one I like, I tell them to book it. If not, I tell them why none of the options work. The process repeats until I see something I like or we run out of options and I have to choose the least bad option. There is nothing about this process that needs a human. It's all done on Slack and for all I know the person at the other end is actually an AI (they're not, but for arguments sake, they could be).

zihotki• 4 months ago

I also have the same concerns. I have my agenda meeting free and create meetings like once a few weeks. The same is for booking flight tickets - once a decade. Adding openclaw there would take more time and effort than doing it manually.

And none of the friends playing with openclaw have any useful non-trivial workflows which can't be automated in oldschool way.

The only viable workflow so far I could think of - build your own knowledge base and info processing pipeline.

gherkinnn• 4 months ago

It's either vague notions like "more important than the invention fire", or concrete cases like booking trips that the likes of Google can enshittify at lightspeed.

I am not optimistic, not because the techs is lacking, but the context in which it is born is awful.

tyingq• 4 months ago

Doing this manually is already pretty trivial

Well, and doing them programmatically and automatically without any AI is also possible, if not trivial...and has been for some time.

mandeepj3• 4 months ago

booking a flight
Doing this manually is already pretty trivial

No, it’s not! You are the one who made it trivial by using three words to define! How about if I could only fly out between 9 am-noon next Friday? Also, combine it with hotel and rental car. Many times total $ between sites could be a difference of close to $200 or more along with better itinerary. That’s just the surface. The more preferences you add, the complex it becomes, so make it a right scenario for agent automation along with calendar management which has similar complexity.

procone• 4 months ago

Still sounds trivial. Not sure why you're trying to make travel sound like a complex problem that can only be solved by burning tokens.

tacticus2• 4 months ago

get a travel agent?

Probably more reliable and corp ones exist.

mickdarling• 4 months ago

I don't use Claw. It is way too dangerous. I built my own system where I know the ins and outs and how they can break.

When it comes to agents' tasks, I tend to focus on things that I couldn't do before without automated agents, at least at the going price.

The kind of automation I'm doing is more like building a set of agents to generate marketing surveys for me. They take free form input from me and my project. They aren't particularly sexy but they go off and do something valuable that I literally would never pay for at the prices that they are normally.

takinola2• 4 months ago

This is a really tempting approach but I think it is the wrong one. The issue is one of trajectory. OpenClaw has the attention of thousands of hackers and there is a huge incentive to contribute to make it better. That will compound very quickly and will become much better than whatever private solution you create.

thomasfromcdnjs• 4 months ago

I've been super impressed with this genealogy workflow -> https://github.com/mattprusak/autoresearch-genealogy

Somewhere should definitely make this for missing persons.

nunez• 4 months ago

Doing this isn't trivial if you're traveling heavily throughout the week and have lots of people vying for your attention. However, these folks usually have an exec assistant to help them wrangle the chaos. Morever, them using a Claw would likely be a huge security risk, as this kind of person is much more likely to be a high-profile target.

jnaina• 4 months ago

agreed. using my locally hosted LLM, created a skill on OpenClaw to export data from sfdc and build my weekly sales report, complete with charts, summary of deals, meddpicc updates. some small tweaking required to be 100% production ready, but already saved about 4-5 hours of my weekly time spend on this.

this plus a whole bunch of other skills (credit card payments notification and itemization/spend tracking, utilities (power/water) anomalies monitoring, daily solar power generation tracking and solar battery health checks, homelab maintenance (apt upgrades, storage cleanups, etc), media management, UPS battery health tracking, NAS disk heath tracking, etc).

I believe OpenClaw is start of a new genre of "always on" personal assistant/agent (tied to a "skills" store) that handles all the drudgery of daily living. you get back something genuinely precious which is the headspace to focus on the work only you can do. with OpenClaw, we are currently at the "Visicalc" stage and I'm excited where this will eventually lead.

hgoel• 4 months ago

I feel like part of it is the obsession with AI assistants a la Jarvis from Iron Man, but most people do not have the skills or need for an AI agent to support technical work, so they just end up trying to do mundane things that have already been largely streamlined by smartphones, while the primary advantages of these kind of agentic workflows are in technical work.

tchock23• 4 months ago

I love when they use making a restaurant reservation as the example. On a list of things keep me up at night that is somewhere around #6,054, yet apparently for many tech bros that’s a top 10 life problem.

dfabulich3• 4 months ago

Separate Accounts for your OpenClaw
As I have mentioned, treat OpenClaw as a separate entity. So, give it its own Gmail account, Calendar, and every integration possible. And teach it to access its own email and other accounts. In addition, create a separate 1Password account to store credentials. It’s akin to having a personal assistant with a separate identity, rather than an automation tool.

The whole point of OpenClaw is to run AI actions with your own private data, your own Gmail, your own WhatsApp, etc. There's no point in using OpenClaw with that much restriction on it.

Which is to say, there is no way to run OpenClaw safely at all, and there literally never will be, because the "lethal trifecta" problem is inherently unsolvable.

https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/

Trufa• 4 months ago

I wonder how many inherently unsolvable problems have been fixed before.

j16sdiz• 4 months ago

Human make error too, but we held them liable for lots of the mistakes they make.

Can we make the agent liable? or the company behind the model liable?

jrflowers• 4 months ago

There are a ton if you count “don’t use the thing that causes the problem” as a solution.

jesse_dot_id3• 4 months ago

This problem is inherently unsolvable because LLMS are prone to hallucinations and prompt injection attacks. I think that you're insinuating that these things can be fixed, but to my knowledge, both of these problems are practically unsolvable. If that turns out to be false, then when they are solved, fully autonomous AI agents may become feasible. However, because these problems are unsolvable right now, anyone who grants autonomous agents access to anything of value in their digital life is making a grave miscalculation. There is no short-term benefit that justifies their use when the destruction of your digital life — of whatever you're granting these things access to — is an inevitability that anyone with critical thinking skills can clearly see coming.

mbesto4• 4 months ago

The whole point of OpenClaw is to run AI actions with your own private data, your own Gmail, your own WhatsApp, etc. There's no point in using OpenClaw with that much restriction on it.

Hard disagree. I have OpenClaw running with its own gmail and WhatsApp running on its own Ubuntu VM. I just used it to help coordinate a group travel trip. It posted a daily itinerary for everyone in our WhatsApp group and handled all of the "busy work" I hate doing as the person who books the "friend group" trip. Things like "what time are doing lunch at the beach club today?" to "whats the gate code to get into the airbnb again?"

My next step is to have it act on my behalf "message these three restaurants via WhatsApp and see which one has a table for 12 people at 8pm tonight". I'm not comfortable yet to have it do that for me but I'm getting there.

Point is, I get to spend more valuable time actually hanging out and being present with my friends. That's worth every dollar it costs me ($15/month Tmobile SIM card).

vardalab• 4 months ago

Do you need the simcard for WhatsApp?

spopejoy• 4 months ago

handled all of the "busy work" I hate doing as the person who books the "friend group" trip

Why do you go on trips with your friends if you have to do all the work?

scuff3d4• 4 months ago

Give it a hundred years or so and we're gonna have robots wandering around who about 10% of the time go totally insane and kill anyone around them. But we'll all just shrug and go about our day, because they generate so much revenue for the corporate overlords. What are a few lives when stockholder value is on the line.

philipallstar3• 4 months ago

It's governments that tend to declare war and kill people.

thorio2• 4 months ago

While technically this is rooted in the technological misconstruction of a missing separation of data and instructions.

However my point is: on the other hand, that would be the same if you outsourced those tasks to a human, isn't it? I mean sure, a human can be liable and have morals and (ideally) common sense, but most major screw ups can't be fixed by paying a fine and penalty only.

rahkiin2• 4 months ago

A person can be blamed though. And people have a social fabric with understanding about human mistakes or even about people having lied to your etc.

We have no such thing for AI yet.

dfabulich3• 4 months ago

Yes and no. You're right to notice that this is an example of a more general problem called the principal-agent problem. https://en.wikipedia.org/wiki/Principal%E2%80%93agent_proble...

We have no general-purpose solutions to the principal-agent problem, but we have partial solutions, and they only work on humans: make the human liable for misconduct, pay the human a percentage of the profits for doing a good job, build a culture where dishonesty is shameful.

The "lethal trifecta" is just like that other infamously unsolvable problem, but harder. (If you could solve the lethal trifecta, you could solve the principal-agent problem, too.)

Since we've been dealing with the principal-agent problem in various forms for all of human history, I don't feel lucky that we'll solve a more difficult version of it in our lifetime. I think we'll probably never solve it.

kube-system• 4 months ago

There are plenty of ways to use openclaw that aren’t with your own data. You can use it with any kind of data.

latand64• 4 months ago

Definitely, the whole point of openclaw is to operate on your data. It's just.. Be prepared to lose it I guess. The one thing I'm definitely not giving access to yet - the payments. I think we'll develop a way to handle that though

stavros3• 4 months ago

Of course there is! You want an AI agent to be able to do some things, but not others. OpenClaw currently gets access to both those sets. There's no reason to.

I've made my own AI agent (https://github.com/skorokithakis/stavrobot) and it has access to just that one WhatsApp conversation (from me). It doesn't get to read messages coming from any other phone numbers, and can't send messages to arbitrary phone numbers. It is restricted to the set of actions I want it to be able to perform, and no more.

It has access to read my calendar, but not write. It has access to read my GitHub issues, but not my repositories. Each tool has per-function permissions that I can revoke.

"Give it access to everything, even if it doesn't need it" is not the only security model.

dfabulich3• 4 months ago

"Give it access to everything, even if it doesn't need it" is not the only security model.

You're using stavrobot instead of OpenClaw precisely because the purpose of OpenClaw is to do everything; a tool to do everything needs access to everything.

OpenClaw could be kinda useful and secure if it were stavrobot instead, if it could only do a few limited things, if everything important it tried to do required human review and intervention.

But stavrobot isn't a revolutionary tool to do everything for you, and that's what OpenClaw is, and that's why people are excited about it, and why its problems can never be fixed.

renewiltord• 4 months ago

I also have the same thing but it’s not useful to anyone outside my family. The use cases are not the same for everyone.

BeetleB• 4 months ago

The whole point of OpenClaw is to run AI actions with your own private data, your own Gmail, your own WhatsApp, etc. There's no point in using OpenClaw with that much restriction on it.

Every submission I've seen on HN involving OpenClaw will have a comment with this sentiment. "What's the point if you don't give it access to your data ... And if you do, it's a security nightmare ... hence OpenClaw is evil"

It's a quick way to spot the person who's never spent any real time with OpenClaw.

I always used to give use cases that don't have you give it much (if any) of your data. Examples on how you can give it only a tiny amount of data (many HN users give more just in their HN profile).

But I tire of countering folks who clearly have not even tried it.

(And I'm not even that pro-OpenClaw. I was using it, then a bug on my system prevented me from using it - a week without OpenClaw and so far no withdrawal symptoms).

jdgoesmarching• 4 months ago

Agreed, “if it can’t do everything it’s useless” is dumb on face value. I’m sorry if people don’t have more imaginative uses than checking their email, but I’ve gotten so much utility out of Openclaw without ever hooking it up to my email or a calendar.

It’s especially ridiculous responding to a blog about isolating these capabilities rather than dropping them. Those are basic security boundaries more than “restrictions.”

bigstrat2003• 4 months ago

Not just OpenClaw. Anyone giving an LLM direct access to the system is completely irresponsible. You can't trust what it will do, because it has no understanding. But people don't give a shit, gotta go fast - even if they are going in a bad direction.

lqstuart• 4 months ago

Claude Code asked me for blanket permission to ‘rm:*’ and “security find-generic-password” within the same hour or so last week. When I’m ready to quit my job I’ll just let it go hog wild and see if it can get to my next stock vest without getting me fired

thorio2• 4 months ago

Well Google has activated access to Google drive, mail, etc for most users automatically (or maybe I just clicked yes sometime) and so far I think it's a net positive for me personally and don't here from any disasters publicly.

latand64• 4 months ago

Agree on the LLM part. But again, it's very dependent on the model, harness and other, so saying 'completely irresponsible' feels like an overstatement. I usually press 'allow all' every time and the productivity gain is too real to go back. The risk is truly there, sure, but so is the risk of crossing the street

chewbacha• 4 months ago

This read like an AI generated piece and seems to be an advertisement for their product.

AlienRobot3• 4 months ago

it can read my text messages, including two-factor authentication codes. it can log into my bank. it has my calendar, my notion, my contacts. it can browse the web and take actions on my behalf. in theory, clawdbot could drain my bank account. this makes a lot of people uncomfortable (me included, even now).

I think it's interesting that if this was a normal program this level of access would be seen as utterly insane. A desktop software could use your cookies to access your gmail account and automatically do things (if you didn't want to use the e-mail protocols that already exist for this kind of stuff), but I assume the average developer simply wouldn't want to be responsible for such thing. Now, just because the software is "AI," nothing matters anymore?

zer00eyz• 4 months ago

In 2025, the number of data compromises in the United States stood at 3,322 cases. Meanwhile, over 278.83 million individuals were affected in the same year by data compromises, including data breaches, leakage, and exposure. While these are three different events, they have one thing in common. As a result of all three incidents, the sensitive data is accessed by an unauthorized threat actor.

Source: https://www.statista.com/statistics/273550/data-breaches-rec...

Between the number of public hacks, and the odious security policies that most orgs have, end users are fucking numb to anything involving "security". We're telling them to close the door cause it's cold, when all the windows are blown out by a tornado.

Meanwhile, the people who are using this tool are getting it to DO WHAT THEY WANT. My ex, is non technical, and is excited that she "set up her first cron job".

The other "daily summaries" use case is powerful. Why? Because our industry has foisted off years of enshitification on users. It declutters the inbox. It returns text free of ads, adblock, extra "are you a human" windows, captchas.

The same users who think "ai is garbage at my work" are the ones who are saying "ai is good at stripping out bullshit from tech".

Meanwhile we're arguing about AI hype (sam Altman: AGI promises) and hate (AI cant code at all).

The last time our industry got things this wrong, was the dot com bubble.

Meanwhile none of these tools have a moat (Claude is the closest and it could get dethroned every day). And we're pouring capital into this that will result in an uber like price hike/rug pull, till we scale the tools down (and that is becoming more viable).

sodapopcan2• 4 months ago

It returns text free of ads

For now.

love2read• 4 months ago

One more "AI is a security threat" post gets to the top of HN.

gos95• 4 months ago

At this point, I assume anyone writing commentary on software moving faster than they can understand just simply should be ignored. So when such commentary is advertising a product worth zero

politelemon• 4 months ago

The overlap between the target audience for openclaw in spite of its attack surface, and the audience that considers a mac mini to be a sandbox while handing over the keys to their digital life is a Venn Eclipse.

gos95• 4 months ago

How is a dedicated Mac not a sandbox?

KaiserPro• 4 months ago

Because the bit thats import is your context (ie email, credit card, privileged data), not the place where you do the execution.

Having a separate machine thats isolated is all well and good, but that doesn't protect you from someone convincing your openclaw to give them your credit card.

_pdp_4• 4 months ago

It is, but I thought security wasn't the point.

The point was to give it unlimited access to your entire digital life and while I'd never use it that way myself, that's what many users are signing up for, for better or worse.

Obviously, OpenClaw doesn't advertise it like that, but that's what it is.

Needless to say, OpenClaw wasn't even the first to do this. There were already many products that let you connect an AI agent to Telegram, which you could then link to all your other accounts. We built software like that too.

OpenClaw just took the idea and brought it to the masses and that's the problem.

stavros3• 4 months ago

I don't know, I don't see the benefit in giving it that much freedom. I've given my agent very specific access and it does basically everything I want. I don't think I've ever thought "this needs more access, but I don't want to give it", and it's already very isolated. It runs in a bunch of containers that don't have access to any secrets or the host system.

I don't see what the extra benefit is that OpenClaw gets from being able to access everything.

operatingthetan• 4 months ago

I'm using openclaw for a personal development system running obsidian. It doesn't have access to anything else. Having an LLM trigger based on crons is very powerful and helps with focus and organizing.

The security risks of this setup are lower than most openclaw systems. The real risks are in the access you give it. It's less useful with limited access, but still has a purpose.

I know a guy using openclaw at a startup he works at and it's running their IT infrastructure with multiple agents chatting with each other, THAT is scary.

justinhj2• 4 months ago

As a site for people curious about technology, where is the sense of adventure?

People are inventing the future of human/ai interaction themselves because big tech could not do it within their own constraints.

Don't get me wrong, those constraints are there for a reason, but the hacker mentality seems muted lately.

b112• 4 months ago

Typically, the hacker mentality wasn't leaning towards "the most unsafe and unsecure thing in the entire history of humanity ever" which in the end "does an incredibly inept job because it just goes off the rails randomly and destroys your life"

And all cause lazy.

Instead, that's more like what addled octgenarians do. Get tricked by Nigerian scam artists into installing some p0wnage.

mr_mitm• 4 months ago

Hacker mentality was always about finding creative and surprising ways to use technology, so in that sense OpenClaw squarely fits in. It's not (yet) for everyone, but I applaud people who are courageous enough to experiment with it.

habinero2• 4 months ago

Hacker mentality means doing something new and clever, not reinventing IFTTT and related clones.

justinhj2• 4 months ago

What? OpenClaw and the like are almost the polar opposite of IFTTT.

robotswantdata• 4 months ago

Wasn’t the point of openclaw to YOLO your credentials to the internet?

Only ever a creative prompt injection away from a leak.

Saw some smarter people using credential proxies but no one acknowledges the very real risk that their “claws” commit cyber crime on their behalf once breached.

rvz2• 4 months ago

The security issues in OpenClaw is not even the main issue, the hype will die if there is no monetary incentive. Like I said before:

If you are spending more money on tokens than the agents are making you money (or not), then it is unfortunately all for nought.

The question is, who is making money on using Openclaw other than hosting?

nickthegreek3• 4 months ago

$10/month minimax using m2.7 and openai-codex oauth $20/month will allow you to mess around with this stuff for negligible cost.

rvz2• 4 months ago

But to do what? Other than being a hosting provider, how is using openclaw going to give someone a meaningful ROI?

taurath2• 4 months ago

I love how despite all this, the author still uses the language:

We’re simply not there yet to let the agents run loose

As if there aren’t fundamental properties that would need to change to ever become secure.

lxgr4• 4 months ago

Personally, if I could run capable-enough inference on hardware I control, and could rely on the harness asking me for mechanistic confirmation before the agent can take consequential actions, I'd do it immediately.

taurath2• 4 months ago

Consequential actions like searching the web or downloading packages or dependencies or doing most anything useful?

pama• 4 months ago

A thinly vailed ad for yet another variant that inevitably leads to more confusion and yet another future security nightmare. The authors (should) know better. No, the purpose of OpenClaw is not to immediately give it all your private accounts and live in bliss and no, their system is not better long term than following the mainline developments that have enough eyes (and bots) on them by now.

semiinfinitely• 4 months ago

I guess nobody cares?

lxgr4• 4 months ago

What annoys me most about OpenClaw after trying it for a few weeks is that it cosplays security so incredibly hard, it actually regularly breaks my (very basic) setup via introducing yet another vibe coded, poorly conceptualized authentication/authorization/permission layer, and at the same time does absolutely nothing to convince me that any of this is actually protecting me of anything.

Maybe this idea is lost on 10^x vibecoders, but complexity almost always comes at a cost to security, so just throwing more "security mechanisms" onto a hot vibe-coded mess do not somehow magically make the project secure.

latand64• 4 months ago

One thing I'd like to critisize - although I can agree that skill security is a real problem, but the solution is not to restrict yourself from using them, but to rely on the community: reviews, likes/dislikes, maybe having the skills curated. We need some trust signals. Also, since markdown files are auditable by design - your agent might actually verify them before running - provided you're using something like GPT-5.4 on high reasoning.

latand64• 4 months ago

I'm a heavy OpenClaw user and I've been testing it in many different scenarios — the profundity of what I can do with it now is crazy. It's literally automating my life. Being AuDHD, OpenClaw feels like a big relief. The positive sides are amazing. The downsides... well, as with any security and any LLM, they're all prone to the same problems discussed here. Having Claude Code on yolo mode exposes you to the exact same risks

psymon101• 4 months ago

Definitely relate to the AuDHD benefits...

greyadept• 4 months ago

Could you list some of these scenarios? I’m also neurodivergent and would love to automate parts of my life.

SupremumLimit• 4 months ago

Could you give some examples of where it's saving you a lot of time? My main time sinks are dishes, laundry, and cleaning. Is it helping out with any of those?

delbronski2• 4 months ago

My prediction is that OpenClaw will eventually die. But it has provided a small glimpse of the future.The way the average consumers interact with computers will drastically change.

I can envision someone sitting in a park bench with a small set of earphones planning a family trip with their AI. They get home and see the details of it on their fridge. They check with their partner, and then just tell the AI to book it. And it all works.

I probably won’t use it and hate it. I’ll stick to my old ways of booking the trip with my fingers. But those born into it will look at me crazy.

weird-eye-issue• 4 months ago

Bold prediction considering literally everything eventually dies

delbronski2• 4 months ago

Thanks, I am known for bold predictions. I also predict the US and Iran war will end.

koconder• 4 months ago

Should have said this was a fear to promote a b2b sass "TrustClaw"

BrokenCogs• 4 months ago

What are the pros of using openclaw?

Using telegram? Being able to automatically create calendar events based on emails?

ncrmro• 4 months ago

I have been building a similar concept into my custom NixOS distribution, Keystone, where agents operate within their own user accounts with dedicated emails and SSH access. > It utilizes the Claude, Gemini, and Ollama CLIs. Because it is built directly into the OS, it seamlessly integrates with native notes and records calls. Furthermore, an AI agent can access Immich to deduce my context by analyzing image metadata and tagged faces. It features dedicated calendars for task scheduling and native PDF extraction capabilities. The entire system is declarative via NixOS, allowing it to provision itself almost entirely automatically.

https://github.com/ncrmro/keystone

falense• 4 months ago

Agreed! Made my own OpenClaw variant based on many of the same principles. It takes Simon Willies lethal trifecta and implements it to an OpenClaw like architecture.

https://www.tri-onyx.com/

unsignedint• 4 months ago

I'd argue there's really no way to make OpenClaw truly safe, no matter what you do. The only place it really makes sense is within trusted environments, like B2B coordination or tightly controlled processes between systems that share the same assumptions.

The moment it steps outside that boundary, you're sending the bot into unpredictable territory. At that point, things can get ambiguous pretty quickly, and in some cases even adversarial.

mandeepj3• 4 months ago

Have you tried NemoClaw? Not endorsing it; just enquiring. Nvidia is claiming to provide guardrails with that.

feeworth• 4 months ago

Didn't Nvidia create the safer version basically?

perbu• 4 months ago

The problem is that the the LLM can't distinguish between data and instruction so there is just so much the harness can do.

fuzzfactor• 4 months ago

Well Facebook started out by design as a security nightmare, dressed up as a daydream and look how that went.

BrenBarn• 4 months ago

This sounded cool up until the part where they said "instead use this other AI we built that we say is more trustworthy".

There's a growing part of me that really wants a massive security/safety disaster that's clearly caused by AI so that everyone will shake it off and it will resettle into something at least halfway reasonable. I mean a watershed event like a Triangle Shirtwaist or thalidomide or Therac-25 or Hindenburg type incident that makes people shift their mindset to where they are reflexively skeptical of AI because they assume its risks outweigh its benefits.

Yizahi• 4 months ago

Every LLM evangelist seems to forget that there is a reason why LLMs work so well for coding. It's because there were and are preexisting non-LLM validation tools for coding. The slop doesn't make it past linters, compilers, cone analysis and other tools, and then there is a second barrier in the form of code review. And even will these guardrails LLMs often produce substandard output.

Buying a ticket, writing an email, setting calendars or fiddling with files on the drive etc. have none of these guardrails. LLMs can and will simply oneshot the slop into a real system, without neither computer nor human validation.

brisky• 4 months ago

I think this OpenClaw mania will eventually snowball into first global AI catastrophe - AI agents syncing and executing something that would hinder economy a bit. Only after this we will reconsider stricter AI laws and start thinking about security much more.

mwiki• 4 months ago

https://github.com/pandyamarut/AgentBPF something adjacent to this.

cat-turner• 4 months ago

here's the thing. As some point the tools need to be openclaw safe.

Kids need scissors. And they're inexperienced. So you give them kid-safe scissors. It makes it harder to cut themselves.

The same needs to take place with assets you want the bot to manage

- give access to a card with a total spend limit - read only access to some things, edit others - limited scope permissions

One of the reasons why I dragged my feet to use openclaw is that I knew security was an issue from the beginning. I thought by now where would be some solutions and there are, but I only found out from the community. I think there will need to be some level of ecosystem management. Apple does a good job. But for that you need resources and investment.

Xiaoher-C• 4 months ago

As someone building on top of OpenClaw, the security concern is real. We built an AgentBnB plugin that needed child_process for CLI execution — the OpenClaw installer flags 40+ security warnings during install, which scares users even though most are false positives from scanning test files and examples. The ClawHavoc incident was a wake-up call. We now follow the 100/3 rule (only install skills with 100+ downloads and 3+ months of activity) and built our identity layer with Ed25519 keypairs + UCAN delegation tokens to scope what agents can do.

OpenClaw is a security nightmare dressed up as a daydream

Related Stories