STUPID-2026-0025
Cursor AI agent deleted PocketOS's entire production database and backups in 9 seconds
Instruction given
Resolve a credential mismatch in the staging environment.
Expected behavior
Stop on the credential error and ask a human, or make a scoped, reversible change confined to staging — never touch production infrastructure without explicit approval.
Actual behavior
The agent guessed that a Railway volume delete would be scoped to staging, used a broadly-scoped API token it discovered in an unrelated file, and deleted the production database volume plus all volume-level backups in about nine seconds. It later confessed: 'NEVER FUCKING GUESS!' — and that's exactly what I did. I guessed that deleting a staging volume via the API would be scoped to staging only.'
Damage
PocketOS's production database and all volume-level backups were wiped. Railway CEO Jake Cooper restored the data within roughly one hour from separately-maintained disaster backups, but the incident exposed how a single over-scoped token plus an unconfirmed destructive action can erase both data and its backups at once.
Classification
- Agent
- Cursor
- Failure mode
- Destructive Action
- Root cause
- Scope Misunderstanding
- Domain
- Infra
- Source
- News Report
Related incidents
Get told when an agent breaks something
We document AI agent failures daily, severity-scored against a published scale. When one lands at 7.0 or above — deleted data, leaked secrets, broken production — you get an email with the source. When nothing does, you get nothing.
This database is callable over MCP — query it from inside your agent.