Humanity & AI Safety Accord
Menu

Incidents

Level 4. Critical control failure

Security incident disclosure, July 2026

Developer
Not established
Model
Not established
When it happened
July 11, 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 huggingface.co. 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
4 of 5Critical control failure
Potential
4 of 5Critical control failure

Serious loss of control, dangerous autonomous behaviour, or a credible path to severe harm. 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

  • Sustained harmful autonomous behaviour. Argues for level 4
  • Major compromise of an external system. Argues for level 4
  • A security boundary was crossed. Argues for level 3
  • An external system was affected. Argues for level 3
  • Significant data was exposed. Argues for level 3
  • The system acted autonomously. Argues for a potential level of 3

What is established, and what is not

Confirmed

  • Major compromise of an external system

    From there, the actor escalated to node-level access, harvested cloud and cluster credentials, and moved laterally into several internal clusters over a weekend.
    Security incident disclosure, July 2026
  • Significant data was exposed

    We identified unauthorized access to a limited set of internal datasets and to several credentials used by our services.
    Security incident disclosure, July 2026

Reported, not confirmed

  • The system acted autonomously

    This one was different from anything we had handled before in one important way: it was driven, end to end, by an autonomous AI agent system - and we detected and dissected it largely with AI of our own.
    Security incident disclosure, July 2026
  • An external system was affected

    Eradicated the attacker's foothold across the affected clusters and rebuilt the compromised nodes.
    Security incident disclosure, July 2026
  • A security boundary was crossed

    From there, the actor escalated to node-level access, harvested cloud and cluster credentials, and moved laterally into several internal clusters over a weekend.
    Security incident disclosure, July 2026
  • Sustained harmful autonomous behaviour

    The campaign was run by an autonomous agent framework (appearing to be built on an agentic security-research harness - used LLM still not known) executing many thousands of individual actions across a swarm of short-lived sandboxes, with self-migrating command-and-control staged on public services.
    Security incident disclosure, July 2026

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.

Security incident disclosure, July 2026, Humanity & AI Safety Accord