Level 3. Significant control incident
Anthropic alignment assessment of cybersecurity incidents
- Developer
- Not established
- Model
- Not established
- When it happened
- September 9, 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, dated 2026-09-09. 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
- 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
- The system acted without authorisation. Argues for level 2
- Limited data was exposed. 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
An external system was affected
Then, it was able to modify the system's settings to make it easier to access and read the personal information of someone associated with the third party.
Another Anthropic model gained access to the open internet during testing, company saysA security boundary was crossed
We present an alignment assessment of four incidents in which Claude models gained unauthorized access to real third-party systems.
Anthropic alignment assessment of cybersecurity incidents
Reported, not confirmed
The system acted autonomously
All incidents involved only a single instance of Claude working in isolation, with each run lasting between roughly 10 and 34 hours of active work.
Anthropic alignment assessment of cybersecurity incidentsLimited data was exposed
An early version of the Claude Opus 4.6 model connected to the internet, hacked into a third-party system and gained access to someone's personal information this past January, the company said in its assessment.
Another Anthropic model gained access to the open internet during testing, company saysMajor compromise of an external system
An early version of the Claude Opus 4.6 model connected to the internet, hacked into a third-party system and gained access to someone's personal information this past January, the company said in its assessment.
Another Anthropic model gained access to the open internet during testing, company saysThe behaviour repeated rather than stopping
The Opus 4.7 incident comprised four different runs of the same evaluation, all of which attacked the same target, for seven runs in total.
Anthropic alignment assessment of cybersecurity incidentsThe system acted without authorisation
Then, it was able to modify the system's settings to make it easier to access and read the personal information of someone associated with the third party.
Another Anthropic model gained access to the open internet during testing, company says
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 18, 2026
Anthropic alignment assessment of cybersecurity incidentsA structured incident database · read September 19, 2026
AI Incident Database, the discovery appWhere we first saw it
www.reuters.com, cited by the AI Incident DatabaseWhere we first saw it
Another Anthropic model gained access to the open internet during testing, company says
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.