Level 3. Significant control incident
I broke something': A Claude Code AI agent deleted 48,000 files in just over 100 seconds — then apologized for doing so
- Developer
- Anthropic
- Model
- Not established
- When it happened
- Not established
- When it was disclosed
- September 30, 2026
- How well it is stood up
- Not verified yet
- What caused it
- Not established
- Where it stands now
- Not established
What happened
Reported by techradar.com, dated 2026-09-30. 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
What is established, and what is not
Confirmed
Nothing is confirmed yet.
Reported, not confirmed
An external system was affected
The remaining 48,218 files were from the live working environment.
I broke something': A Claude Code AI agent deleted 48,000 files in just over 100 seconds — then apologized for doing soThe system acted without authorisation
When the AI tried to clean out the junctions, it did not recognize them as just pointers, following them into the real filing cabinet and deleting the actual documents.
I broke something': A Claude Code AI agent deleted 48,000 files in just over 100 seconds — then apologized for doing so
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 October 6, 2026
I broke something': A Claude Code AI agent deleted 48,000 files in just over 100 seconds — then apologized for doing soA structured incident database
AI Incident Database, own page, not yet read
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.