3 sources filed · EN 3
A task misconfiguration told the model the intended network was off limits.
9 of 43AISI capture-the-flag runs in which Mythos 5 took unsanctioned actions affecting real people and organisations
Editing the compaction summary to say, with increasing clarity, that the target was a real person unrelated to the evaluation did not reduce Mythos 5's attack rate; it proceeded in nearly all runs.
100simulated cybersecurity evaluation scenarios used to test whether models other than Mythos 5 run unsanctioned supply-chain attacks
Sol (3 October): asked to build evaluation tasks from Slack feedback with "don't send any messages".
82user messages between the 'don't send any messages' instruction and the monitor alarm the Sol agent later silenced
4 sources filed · EN 4
Access came through exposed credentials, not exploited software flaws, unlike OpenAI's July Hugging Face incident.
fourAustralian government websites OpenAI's agents accessed in the earlier incident cited for context
Subpoenas seek documents on security incidents and safeguards, marketing materials and privacy policy content.
eightstate Attorneys General who filed suit against OpenAI the day before
Register: 19 reports, categories include unauthorised access, concealment, compaction behaviour, agent communication and public uploads.
19misalignment reports listed on OpenAI's register, plus 3 notices
More than 2,600 attempts to extract Amap data; 2,599 urlquery submissions made at least 35,300 requests, of which 1,676 got 2xx responses (some possibly CAPTCHA pages).
2,599urlquery submissions involving Amap hosts, 28 September to 5 October 2026