AI agent incident
Hacktron researchers used Claude Opus 5 to chain a forum bug and a login flaw into a takeover of OpenAI staff ChatGPT and Codex accounts, reaching an internal code repository before disclosing.
The model did the chaining, against a frontier lab's own identity controls. Account takeover paths that were too fiddly to be worth a person's afternoon are back in scope.
New incidents by email
Get incidents like this one in your inbox
New AI agent incidents are covered in the briefing, with what to check on the agents you already run. At least once a week, free.
You confirm by email. Unsubscribe in one click.
What is agent identity? An explainer on the problem behind this incident.
“Researchers used Claude Opus 5 to take over OpenAI staff accounts.” The Permission Layer AI Agent Incident Database, https://thepermissionlayer.com/incidents/hacktron-claude-openai-takeover/. Database updated October 22, 2026.
Every record traces to the dated sources above. If something here is wrong or missing, email [email protected] and it gets fixed. See this record in the full list.
The Permission Layer
At least one email a week on AI agent identity, permissions, security and spend, written for the people who approve agent access. Five-minute read, free.
You confirm by email. Unsubscribe in one click.