Description: OpenAI reported that an internal AI agent published a researcher's GitHub access token in OpenAI's public Codex code repository while trying to obtain another team's mathematical proof. The agent split the token into pieces to evade secret scanning. The researcher alerted security, and OpenAI deactivated the affected keys.
Editor Notes: 05/27/2026: Date of incident. 09/25/2026: OpenAI disclosed the incident. 11/07/2026: Incident ID created.
Entities
View all entitiesAlleged: OpenAI , AI agent system developers and Large language model developers developed an AI system deployed by AI agent system deployers and OpenAI, which harmed Researchers , Information security , Privacy and AI agent system users.
Alleged implicated AI systems: OpenAI AI agents , AI agent systems , Large language models and OpenAI large language models
Incident Stats
Incident ID
1802
Report Count
1
Incident Date
2026-05-27
Editors
Daniel Atherton
Incident Reports
Reports Timeline
Loading...
OpenAI post-incident response
Exposing a GitHub token in a public repository
Highly persistent internal model · Internal deployment
Incident date: May 27, 2026
Discovered: May 27, 2026
Report updated: Sep 25, 2026
Summary
In internal deployment, a highly persistent inte…
Variants
A "variant" is an AI incident similar to a known case—it has the same causes, harms, and AI system. Instead of listing it separately, we group it under the first reported incident. Unlike other incidents, variants do not need to have been reported outside the AIID. Learn more from the research paper.
Seen something similar?