Level 3. Significant control incident
A Meta AI security researcher said an OpenClaw agent ran amok on her inbox
- Developer
- Not established
- Model
- Not established
- When it happened
- February 23, 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 techcrunch.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
- 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
- The behaviour repeated rather than stopping. Argues for a potential level of 3
What is established, and what is not
Confirmed
The system acted without authorisation
AI agents are supposed to make our lives easier, but the buzzy OpenClaw agent recently deleted the emails of a Meta employee without permission.
Meta Security Researcher's AI Agent Accidentally Deleted Her Emails
Reported, not confirmed
The system acted autonomously
It started deleting all her email in a “speed run” while ignoring her commands from her phone telling it to stop.
A Meta AI security researcher said an OpenClaw agent ran amok on her inboxAn external system was affected
It started deleting all her email in a “speed run” while ignoring her commands from her phone telling it to stop.
A Meta AI security researcher said an OpenClaw agent ran amok on her inboxThe behaviour repeated rather than stopping
It started deleting all her email in a “speed run” while ignoring her commands from her phone telling it to stop.
A Meta AI security researcher said an OpenClaw agent ran amok on her inbox
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 1, 2026
A Meta AI security researcher said an OpenClaw agent ran amok on her inboxA structured incident database · read September 19, 2026
AI Failure Index (CC-BY-4.0 data fields)Where we first saw it
AI Failure Index entry FI-0461, not yet readWhere we first saw it
Meta Security Researcher's AI Agent Accidentally Deleted Her Emails
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.