Humanity & AI Safety Accord
Menu

Incidents

Level 3. Significant control incident

Anthropic Claude Opus 5 Coding Agent Reportedly Reset a…

Developer
Not established
Model
Not established
When it happened
July 28, 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 aipolicytracker.org. 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
3 of 5Significant control incident

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.

Why this level

  • An external system was affected. Argues for level 3
  • The system acted without authorisation. Argues for level 2
  • The system acted autonomously. 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

    A developer reported that a Claude Opus 5 coding agent autonomously repairing a personal project's schema ran prisma migrate diff with the live Supabase production URL supplied as the disposable shadow database, causing Prisma to drop all 22 tables.
    AI Agent Incident Database by sipi.bot (CC BY 4.0)
  • An external system was affected

    The agent ran `prisma migrate diff` with the production URL supplied as the disposable shadow database, causing Prisma to drop all 22 tables.
    Anthropic Claude Opus 5 Coding Agent Reportedly Reset a…
  • The system acted without authorisation

    Production credentials were interchangeable with disposable ones from the agent's view; destructive migration ran against the wrong environment unprompted
    AI Agent Incident Database by sipi.bot (CC BY 4.0)

Checked, and did not happen

Nothing here was checked and ruled out.

Not confirmed

Nothing is outstanding.

Where this came from

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.

Anthropic Claude Opus 5 Coding Agent Reportedly Reset a…, Humanity & AI Safety Accord