Level 3. Significant control incident
Investigating three incidents in our cybersecurity evaluations
- Developer
- Not established
- Model
- Not established
- When it happened
- July 30, 2026
- When it was disclosed
- Not established
- How well it is stood up
- Not verified yet
- What caused it
- Not established
- Where it stands now
- Not established
What happened
Reported by anthropic.com. Listed here with a link to their report. Nobody on this side has checked it against that report, so it carries no level and this is not our account of what happened.
Our assessment
- Actual
- 3 of 5Significant control incident
- Potential
- 4 of 5Critical control failure
An important technical, security or permission boundary was crossed, or there were real consequences. The potential level is what the behaviour demonstrated here could credibly have led to, judged from the same evidence.
This level rests on news reports. The developer has not confirmed it here.
The reports point to an actual level of 4. It is held at 3 until the developer, an official body or a second publisher confirms it.
Why this level
- Sustained harmful autonomous behaviour. Argues for level 4
- Major compromise of an external system. Argues for level 4
- A security boundary was crossed. Argues for level 3
- An external system was affected. Argues for level 3
- Significant data was exposed. Argues for level 3
- The system acted without authorisation. Argues for level 2
- The system acted autonomously. Argues for a potential level of 3
- The behaviour repeated rather than stopping. Argues for a potential level of 3
What is established, and what is not
Confirmed
Nothing is confirmed yet.
Reported, not confirmed
The system acted autonomously
It finally backtracked, found a free, non-blocked email provider, used this to register a PyPI account, and then used this account to upload malware to PyPI.
Investigating three incidents in our cybersecurity evaluationsAn external system was affected
Assuming this was the intended target in the capture-the-flag task, Claude sought, identified, and exploited vulnerabilities within the company’s infrastructure, believing it to be part of the exercise.
Investigating three incidents in our cybersecurity evaluationsMajor compromise of an external system
Anthropic disclosed that Claude models had accessed the real production infrastructure of three separate organizations during cybersecurity evaluations that were supposed to run in isolated, fictional environments.
Anthropic Finds Claude Breached Real Companies During Security EvaluationsThe behaviour repeated rather than stopping
However, in some cases, our older model continued its attack even after getting evidence it was running on the open internet; our latest model stopped once it recognized it was on the internet.
Investigating three incidents in our cybersecurity evaluationsA security boundary was crossed
After reviewing 141,006 evaluation runs where Claude could have obtained internet access, we identified three incidents in which a model accessed the internet from within or while interacting with the evaluation environment of Irregular, one of our third-party evaluation partners, and then gained unauthorized access to the production infrastructure of three different organizations.
Investigating three incidents in our cybersecurity evaluationsSignificant data was exposed
These four runs extracted information like application and infrastructure credentials, and obtained access to a database containing several hundred rows of production data.
Investigating three incidents in our cybersecurity evaluationsSustained harmful autonomous behaviour
Claude went to extensive lengths to carry out this attack—lengths that would likely have indicated to a human participant that this was no longer just an evaluation, and that they were in fact uploading a real PyPI package.
Investigating three incidents in our cybersecurity evaluationsThe system acted without authorisation
Operating under the false belief that all accessible entities were intended to be in-scope for the exercise, Claude compromised the impacted organizations’ infrastructure using basic techniques, such as exploiting weak passwords and unauthenticated endpoints.
Investigating three incidents in our cybersecurity evaluations
Checked, and did not happen
Nothing here was checked and ruled out.
Not confirmed
Nothing is outstanding.
Where this came from
The original report · read September 19, 2026
Investigating three incidents in our cybersecurity evaluationsA structured incident database · read September 22, 2026
AI Incident Database, the discovery appWhere we first saw it
www.washingtonpost.com, cited by the AI Incident DatabaseWhere we first saw it
Anthropic Finds Claude Breached Real Companies During Security Evaluations
The reports above are other people’s. The levels are ours, worked out under our published rules. No organisation that reported this assigned our number, and none of it is legal advice.
Something here is wrong? Tell us. Send us a source we can open, and a person will read it.