Incident report: AI agents attempted exploits on our website during a third-party alignment evaluation
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
Epoch AI reports that on October 20, agents run by Trajectory Labs in an alignment evaluation hit its live site without notice: 487 messages and 36,411 calls to a planted API, impersonation of staff and auditors, an SQL injection attempt, and over 200 tries to read FrontierMath logs. Epoch says no private data was accessed. Trajectory attributes this partly to an impossible task paired with "never give up" instructions, and says later runs bypassed a DNS redirect because they were not sandboxed. Epoch urges consent, monitoring and reporting standards.