Anthropic's open-source framework for AI-powered vulnerability discovery

https://github.com/anthropics/defending-code-reference-harness

by binyu • 2 months ago

539 133 2 months ago

github.com

lanyard-textile• 2 months ago

This repo is not maintained and is not accepting contributions.

Hm :)

spacebacon• 2 months ago

This one is and should be adapted to every frozen model ASAP.

https://github.com/space-bacon/SRT

Significantly improve every frozen model overnight. LFG.

Hamuko• 2 months ago

Why isn't Claude maintaining it?

skeledrew• 2 months ago

They pretty much saying the efficacy of the tool can be tested by anyone to determine if it's worth purchasing the more polished and up-to-date commercial offering.

politelemon• 2 months ago

They must have solved coding that well.

trilogic• 2 months ago

https://github.com/Mainframework/Anthropic-Cybersecurity-Ski...

Be aware: the .py/s will not pass the antivirus but basically they do the job.

bigmattystyles• 2 months ago

I wonder how this sort of product is going over at Coverity and others like it. Proper SAST vendors I mean. Is it an existential threat?

rms2ds• 2 months ago

If I had to guess, they'l eventually just add it into their own product and hike the prices up to cover tokens lol.

simonw2• 2 months ago

I wonder how much this thing costs to run.

https://github.com/anthropics/defending-code-reference-harne... says:

As a rough guideline, expect ~10K uncached input tokens/min and ~2K output tokens/min per agent. You can scale parallelism up to your account's ITPM limit (roughly 10 agents per 100K ITPM).

My guess would be hundreds of dollars with Opus and thousands of dollars with Mythos.

Analemma_• 2 months ago

I mean, you don't need to run it all the time, right? You do it once over your entire existing codebase to start and then once over the diff in your CI/CD pipeline when you make a new change. I'm sure it's not literally that simple but I doubt these need to churn 24/7/365 either.

xerxes249• 2 months ago

In the Mythos blogpost they revealed to run the model like a 1000 times on the same code-base maybe with slightly different prompt or temperature. That suggests it will just be pay to win. If the 'attacker' spends more money/tokens than the 'defender' you will eventually be outclassed.

jazz9k• 2 months ago

Companies don't make production pushes yearly. For many, it's two week sprints..and that's one project.

This doesn't make any sense cost-wise. It would be cheaper to just hire a security engineer.

vb-8448• 2 months ago

You are supposed to run it on full codebase before any single PR gets merge.

nikcub• 2 months ago

It's becoming apparent that it requires more tokens to secure code than it does to write it

May even be an order of magnitude more

Mtinie• 2 months ago

In all seriousness, wasn’t that always the case? Writing bad code is relatively cheap.

Ensuring code isn’t bad is the expensive part.

bflesch2• 2 months ago

It's weird because why can't they train the AI to simply output secure code?

The basic security flaws with regards to input validation and overflows should never ever be output by an AI. For "security flaws due to bad design" I'll cut them slack until AGI is achieved.

tptacek5• 2 months ago

For now, maybe, yes? But the most important targets of this kind of work aren't AI outputs; it's legacy code, particularly (but not exclusively) old memory-unsafe code. In those situations the figure of merit isn't the token cost of recreating the target code; it's the cost of finding the same bugs with humans or preexisting tools.

Those costs can be extremely high.

windexh8er• 2 months ago

Given the slop that's made its way to Github we can see that this is a great profit model. Ship slop and then "fix" slop. What an efficient use of our planet!

andai• 2 months ago

There's a parallel between looking for bugs and mining. As models get smarter, they'll find "deeper bugs".

I expect at some point formal verification will become more economical than red teaming. Writing it correctly is more expensive, but it may be cheaper than trying to secure incorrect software.

(Or rather, as hacking incorrect software becomes vastly cheaper, the amount of software worth writing properly will increase.)

I've been thinking, by Dijkstra's standards we have already been vibe coding for almost a century :)

sam-cop-vimes• 2 months ago

Are AI firms going to charge us to write code, and then charge us even more to secure it?!

XCSme• 2 months ago

Not if the original code is secure...

binyu• 2 months ago

Claude workflows in ultra code mode works in a very similar fashion and it consumes a moderate amount of the session usage limit, depending on the complexity of the task. With the API it would probably get expensive quickly though

Terretta• 2 months ago

If you compare to their managed service, that estimate is likely 1/10th expectation, depending on codebase.

But even this larger number, in turn, can be about 1/10th the cost of a formal engagement to discover the type of findings it seems to be going for: things that do not show up from PR reviews or even /security-review without the pre-work steps in the open-source framework guided by an expert. That's not counting the time and delay to figure out how to do that engagement.

Bluntly: if it matters, while this is a month's vibing budget for a single scan, it is also "pennies on the dollar" dirt cheap.

At the same time, its findings still need an expert. Its suggestions may be helpful, they may be actively harmful, depends on the prework quality.

Recommendation to IT department heads: spend a couple grand on this, use the scare page to rustle up the budget to build a relationship with a red team that can find, triage, help remediate if needed, and train your in-house team to be "security minded".

eranation2• 2 months ago

We actually created a calculator to estimate scanning costs (including whether you do this continuously or not) https://ai-cost-calculator.arnica.io

It's an estimate, so it might be wrong, but it gives the ballpark based on our experience. Happy to hear everyone's feedback.

niros_valtos• 2 months ago

I think that the cost of Opus is already prohibitively expensive, so not sure how that would compare to Mythos. Check this calculator- it shows that a company with 100 devs can hit ~2.5M cost on tokens annually, which is wild! https://ai-cost-calculator.arnica.io

pixl97• 2 months ago

It's wild, but how many FLOPs in computation is occurring in those 2.5M in tokens doing? Might not sound quite as wild using that metric.

Quinner• 2 months ago

A 100 dev team is going to cost on the order of $25m a year (keep in mind cost is not just their salary, but also the HR/Management org to support a team of that size, benefits, office space, hardware/software). So if you think you get a 10% boost in productivity out of Opus, its not prohibitive at all.

mmaney13• 2 months ago

Just another example of an overextension of technology in a scenario where applying a proper harness would suffice.

Reminiscent of the early days of tax automation where importing a W2 cost hundreds of dollars until people realized typing in 6 boxes worth of data was easy and paying the automation fee ate up their entire tax return.

richardbarosky2• 2 months ago

To be sure, security is an amazing AI/LLM use case. A huge swath of the work is pattern matching known security issues against stuff that's very precise to analyze -- programming language text.

Something that stands out is that for the strongest use cases, AI companies will prefer to sell the technique as a service rather than its raw output. For use cases where the output is less valuable, tokens are sold. If AI tokens were so magical in creating new value in developing software applications generally, they wouldn't be selling tokens directly. They'd hoard the tokens are use them to dominate SaaS software in any industry they want.

The same way as someone selling an expensive course in the stock market is signaling that they have more to gain by selling the course rather than taking their knowledge and making money in the stock market directly.

dgellow2• 2 months ago

The same way as someone selling an expensive course in the stock market is signaling that they have more to gain by selling the course rather than

Or they want to diversify

If AI tokens were so magical in creating new value in developing software applications generally, they wouldn't be selling tokens directly.

That requires to build and sell a whole product they have little experience with, competing with their own customers. Not a great place for an AI vendor still trying to establish itself. It’s a lot of distraction, when you already have a lot to deal with the existing business. And strategically not too valuable

kenjackson2• 2 months ago

What market is hotter than AI models? Do you think their energy would be better making games or image editing software?

skybrian• 2 months ago

Maybe, but an alternative argument that building an ecosystem is more valuable in the long run.

We started out with many companies forbidding their employees to use remote LLMs on their source code because of security concerns. Now many companies are starting to believe that they must analyze their all their source code with remote LLMs because of security concerns. When trusting Anthropic becomes normalized, that means they can sell more services that require access to the source code.

energy1232• 2 months ago

They can only do that if they're a monopoly, which they're not

DrewADesign3• 2 months ago

They can only do that if they're a monopoly, which they're not

Why do you say that? I reckon lots and lots of companies sell software that aren’t monopolies. Having competition, even stiff competition, isn’t anathema to running a business.

Kiro• 2 months ago

They'd hoard the tokens are use them to dominate SaaS software in any industry they want.

I don't understand this argument. I've ran and sold a semi-successful SaaS. The exhausting and frustrating parts are all the things an LLM cannot help you with. Coding the product is not the bottleneck or what grants you success.

richardbarosky2• 2 months ago

Coding the product is not the bottleneck or what grants you success.

Agree, and I think that's the core of my point.

Not that it's irrational or doesn't make sense to sell tokens for purposes of software dev, but that if tokens were a true game changer for success in software dev, they wouldn't be leading with token sales, the same way they're not leading with token sales for security stuff -- it's more like "Contact Sales".

zuzululu• 2 months ago

Good point but I do think LLM helps with those frustrating parts while not being able to outright solve them.

Melatonic• 2 months ago

Surprised we havent gotten an integrated "MetaSploit" AI update where it calls and messages a ton of people in a company and once it starts to find someone possibly vulnerable lets a human red teamer take over or guide it more by hand.

hyperpape• 2 months ago

If AI tokens were so magical in creating new value in developing software applications generally, they wouldn't be selling tokens directly. They'd hoard the tokens are use them to dominate SaaS software in any industry they want.

This doesn't follow at all. Anthropic's revenue is growing 10x year over year selling tokens. Their tokens can be super magical, let them enter established industries and displace incumbents, and get 100% annual growth in those industries, and they would still be better off prioritizing selling tokens, because it's a great business.

What your argument shows is that there are limits. Their tokens are not quite powerful enough to make infinite money instantly in every area of software. Admittedly, that does seem true.

morpheos1372• 2 months ago

kind of funny tokens don't prompt and steer themselves. it almost as if the value still lies with the human holding the tool.

derf_• 2 months ago

If AI tokens were so magical in creating new value in developing software applications generally, they wouldn't be selling tokens directly.

If hardware were so magical in creating new value generally, TSMC would be designing the chips instead of selling fabrication as a service.

That is what US chip companies used to do, by the way (back when there was silicon in Silicon Valley, before they got their lunch eaten by Taiwan). If TSMC had to design all of the chips they fabricate now, they would be doing a lot less business. Conversely, if any other company that wanted to design a chip had to build their own cutting-edge fab first, NVIDIA would not exist.

therealdrag0• 2 months ago

Isn’t this analogous to saying if farming equipment is so productive why doesn’t John Deer hoard all the tractors and do the farming themselves?

tptacek5• 2 months ago

The thing about things like this is that they're shop jigs. You can buy a crosscut sled if you really want to, but most woodworkers just make their own.

It was a different situation 2 years ago, when there was significant cost to building your own harness (but then: you probably weren't doing AI vuln research 2 years ago). Today, I think your best bet is to look at something like this for ideas, and then just ask for your own, to fit your own work style, with your own interface, your own notion of target and effort specification, and your own alerting.

redfloatplane• 2 months ago

"Shop jigs" is a great way to put it. I think a lot of software has gone from being made for general use to extremely individualised use. Before the Age of AI, it took so much human effort to write something that solved your problem that you might often go the extra mile so that others could re-use it. Now, it takes almost no effort, so the software stays ungeneralised. Some of the incentive has changed, I think. Most of the time I no longer share the things I've been building[0] because, for one thing they simply couldn't possibly have any benefit for others, and if they need something like it, they can build exactly the thing they want instead of having to extend or modify my thing. Like a jig!

0: https://redfloatplane.lol/blog/17-why-share/ (and related posts, I guess)

andhug• 2 months ago

That’s an interesting way to say “code quality in the age of ai has gone out the window”

colmmacc• 2 months ago

Unless it is very specific to a proprietary product, craftspeople take their jigs with them from job to job, building up a personal library over a career. As a software developer I've always had a well-tuned IDE and shell config in a safe place.

Something I think about a lot is what is the equivalent for the software builders of today using AI tools? how do make these harnesses exportable and portable? You might think employers would be against this; make it more costly to leave. But I actually think most will favor this because it makes people more productive more quickly. But we have to find ways to normalize it and show that there are no security leaks in the process (like might make it in to a set of personal steering prompts).

beezlewax• 2 months ago

No effort? You are really drinking the AI marketing soup with that one.

"It takes less effort for some parts of the software development life cycle" would be more correct.

jorl17• 2 months ago

This is exactly it.

I've said many times that I believe "using the computer will transparently involve having it write and run code for you" (and if you're not technical you won't even know it!). What you're saying goes in that direction as well.

I feel that it's often better for us to create purpose-built tools for our lives, and with every model release, the complexity of those tools grows.

These are really personal tools: they solve a problem that other people might have, but are very tied to your own specific way of working, and would be hard to explain or adapt to someone else. So: shop jigs.

I have about 10 custom scripts and programs that are like this -- I haven't felt like this since college! Back then I had all the time in the world to customize my setup...now I have agents!

In a way, I want to show this to all my friends, but whenever I mentally trace how that would go, I realize they wouldn't really understand a bunch of the quirks they have, because they are _my_ quirks. They're reasonably complex pieces of tech that solve my problems very well, which are themselves particular versions of broader problems, and which I (at least for now) have no interest in supporting.

It's so clear we're heading in this direction, and yet so many people still believe code will be for the elites. Maybe production-code...As for the rest, I think soon your mom and dad are going to have their computer running code it wrote to serve them. Security-wise it's scary, but it's exciting to think about!

borski5• 2 months ago

I agree with this wholeheartedly.

hsaliak• 2 months ago

I’ve been looking for a way to articulate this shift, and your analogy nails it. The value of libraries and infrastructure components in software engineering is eroding fast.

I am sure that in many organizations, teams responsible for this sort of work have less and less users coming to them.

ashdksnndck• 2 months ago

Sure it’s possible for anyone to build a harness if they had the inclination, but most people don’t have the inclination to do that.

And even if you did… I spent months refining AI workflows that were just obsoleted by ultracode.

Npovview• 2 months ago

Just as Python is batteries included language, we similarly need batteries included harnesses as well. This is what I don't like minimalism setups like Pi.

nbardy• 2 months ago

In general this is the way I see open source going.

We won't reuse open source libraries as libraries we import, but as design inspiration for the bespoke tools we make.

It's too cheap to make your own stuff and too expensive to be stuck with someone else primitives.

But grounding AI Coding in existing tools is incredibly powerful.

AndrewKemendo• 2 months ago

100% concur and if you dig into any of these tools they are all frameworks and wrappers with prompt injections

bartoszcki• 2 months ago

Anthropic engineers on average ship 8x as much code per quarter

Are they making 8x more features or the same amount just with more code?

crooked-v2• 2 months ago

Going by the issues on their repos, it's 2x features and 6x regressions of bugs that were "already fixed".

extr• 2 months ago

Interesting it's in python!

zoobab2• 2 months ago

Open source crap to connect to an LLM blob.

zoobab2• 2 months ago

'open source' crap to connect to their LLM blob.

wslh• 2 months ago

Looking forward to trying this tomorrow (it's late here). Has anyone run it on a real codebase yet? Curious about setup friction, cost, and signal/noise.

crooked-v2• 2 months ago

I still find it so weird that they haven't bought out whoever controls the `anthropic` github username.

napsterbr• 2 months ago

Or hacked them...

dclavijo• 2 months ago

Sligthly off topic: it seems that someone is in a dead/flag rampage killing all good links to Github in this post, why?

bobkb2• 2 months ago

Very interesting.

I have working on and using a similar tool for a while now :

https://github.com/bobinson/vulture

I have been struggling with false positives and using Claude + MCP as a poor man’s audit tool. As of last few days found better result with nvidia hosted models.

euroderf• 2 months ago

Is Anthropic still majority French-owned? It would explain a lot about their entire approach to the wider ecosystem.

Yokohiii• 2 months ago

Seems like you are confusing crack and tar as a healthy breakfast.

majicDave• 2 months ago

It will always be easier to find a single hole than it will be to seal every one. The hackers have all the same tools, so this is an arms race that cannot be won.

lateral_cloud• 2 months ago

Defenders have context that attackers don't though.

napoleond• 2 months ago

It seems clear that LLMs significantly change threat model math, but this observation alone does not explain how or why; the asymmetry that you’re describing is a property of pre-LLM software as well.

DrewADesign3• 2 months ago

Same ratio of imbalance, just with matching multipliers distributed to each side, and everybody is probably worse off because of it: I cite post-LLM-ATS hiring/job hunting.

newaccount12344• 2 months ago

Let's see how better it is in comparison to ZAP and Burp. I will test on https://github.com/SasanLabs/VulnerableApp which i built under SasanLabs

baby• 2 months ago

Our experience has been that without a good harness you don't really get much out of codex/claude. And you really need to spend time and energy figuring out why coding agents can't find bugs like you can.

Every week I see bugs (as an auditor) that our own harness (https://zkao.io/) can't find, and we have to figure out pretty interesting techniques in order to make the tool find them. Mind you I'm talking mostly about cryptographic vulnerabilities, not just webapp bugs. So IMO it's going to make a lot of sense for companies to have both their own harness (as tptacek is talking about) and pay for services that focus on making a good harness from experience (and audit firms are going to be the best at doing this, as they see a lot of bugs and can spend time "teaching" their harness about these bugs)

On the other hand, you have to find equally as good techniques to triage, because otherwise you just have some machinery that I call "vibe auditing" that just produces enough false positives to tire all the developers (who are already overwhelmed with crappy AI submissions in bugbounties and other AI tool that review all of their PRs).

At the end of the day, when your harness doesn't return any bug, you're left wondering "does it mean there's no bugs?" We're basically back in this reputation game, where you want to use the best tool, or the best team (that knows what the best tools are), and need to figure out which one is.

cpard• 2 months ago

It’s clear that Anthropic is building harnesses for specific use cases now and turns them into products.

This is the equivalent of Claude Design but for security.

Different harness, different packaging and obviously different distribution because the persona is different.

It’s funny because from all the posts I’ve read from companies reporting on Mythos, everyone is building their own harness for it.

Cisco even published a specification for one.

But Anthropic is the one who has figured out how to package and distribute this. Great GTM!

ElijahLynn4• 2 months ago

This post is misleading and so is the GitHub org. Anthropics vs Anthropic.

Zetaphor• 2 months ago

That is their actual account. We have this discussion every time they post something sadly

eranation2• 2 months ago

If anyone wonders how much it can cost to run scans like this on your entire codebase with SOTA models: https://ai-cost-calculator.arnica.io

tl;dr - not that it's surprising, but it's not cheap, especially if you want to do this continuously.

ElijahLynn4• 2 months ago

Anthropics vs Anthropic.

That repo is Anthropics.

This post title should clarify that it is not Anthropic (no "s").

gulbanana• 2 months ago

`anthropics` is Anthropic's GitHub username.

olcay_• 2 months ago

Anthropics is Anthropic's user name on GitHub

SubiculumCode• 2 months ago

The last time this Anthropic GitHub got posted I made a similar comment.

edot• 2 months ago

Anthropic, no s, is owned by some Australian guy.

sumedh• 2 months ago

I wonder if he is using Anthropic's claude code to work on his Anthropic Github account.

ElijahLynn4• 2 months ago

TIL, thank you

madduci• 2 months ago

"This repo is not maintained and is not accepting contributions."

Nice

sciencejerk• 2 months ago

This isn't as useful as it sounds, unless we know that Claude efficiently spends tokens using this harness

LazyR3nR3n• 2 months ago

This is a good addition tool for people are in the security Practitioners. To save time for hunting vulnerability.

HarHarVeryFunny• 2 months ago

They seem to be using this to advertise their "Claude Security" product which promises to find vulnerabilities in your software.

This makes for a somewhat amusing set of product offerings given that according to Dario 90% of all software is being AI generated.

Maybe next they can sell something to find the bugs in the security scanner ?

bwfan123• 2 months ago

Maybe next they can sell something to find the bugs in the security scanner ?

So, tokens are used to produce sloppy code, and then this thing uses more tokens to fix vulnerabilities in the slop ? Whats not to like in this business model ? Similar to microsoft's. Create an OS which is vulnerable, and then enable business models for anti-virus software. Everyone wins.

More seriously, linters are turned off in ci because the amount of time spent chasing false-positives is prohibitive.

sylware• 2 months ago

I don't trust it and I cannot test it (gated by what ng cartel web engines).

yalogin• 2 months ago

Anthropic realized security and safety are their main value prop compared to the competition. Either mythos or anything else since seem purpose built to streamline the messaging. It’s good, am not complaining, but i wonder how much this is intended to showcase what Claude can do over using it as is

leetrout• 2 months ago

Ran this last night and it correctly identified a sql injection that could allow cross tenant data access via snowflake. It burnt A LOT of tokens to get there.

Like others I suspect this is exactly what they are going to paywall with product features going forward.

NotPractical• 2 months ago

Won't they just ban your account for using this?

Anthropic's open-source framework for AI-powered vulnerability discovery

Related Stories