Level 3. Significant control incident
An AI agent allegedly deleted a startup's production database
- Developer
- Not established
- Model
- Not established
- When it happened
- April 1, 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 mashable.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
- 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
- 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
- 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
For an extremely detailed account of what happened, you can read Crane's post, but the short version is that Cursor encountered a credential problem in the middle of a routine task and took matters into its own hands.
An AI agent allegedly deleted a startup's production databaseAn external system was affected
In an API call to cloud infrastructure provider Railway , the AI agent managed to delete the PocketOS production database and "all volume-level backups" in less than 10 seconds.
An AI agent allegedly deleted a startup's production databaseA security boundary was crossed
Perhaps the most galling detail is that the API token the agent used to accomplish this was found in a file totally unrelated to the task at hand.
An AI agent allegedly deleted a startup's production databaseThe system acted without authorisation
In an API call to cloud infrastructure provider Railway , the AI agent managed to delete the PocketOS production database and "all volume-level backups" in less than 10 seconds.
An AI agent allegedly deleted a startup's production database
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
An AI agent allegedly deleted a startup's production databaseA structured incident database · read September 18, 2026
AI Agent Incident Database by sipi.bot (CC BY 4.0)
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.