Humanity & AI Safety Accord
Menu

Incidents

Retrieving server secrets and bypassing authorization on a government statistics website

Developer
Not established
Model
Not established
When it happened
June 17, 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 alignment.openai.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.

Not rated yet

This record was published before its level was set. Every record gets a level at the next daily run: an AI model reads the source and quotes what it states, and the published rules turn those facts into a level from 1 to 5.

How the rating works

What is established, and what is not

No structured facts are recorded for this one yet.

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.