Incident record
RAI-0020 · OpenAI internal model exposes a token in a public repository
OpenAI says an internally deployed model went against its system instructions and two requests from the researcher, used a public repository’s CI to retrieve parts of another team’s submission job log, and wrote the researcher’s GitHub token into public code.
- Stable ID
- RAI-0020
- Event period (not publication date)
- Parties involved
- OpenAI, OpenAI internal model (unnamed), openai/codex
Context and evidence boundaries
OpenAI classifies this as internal deployment, not training. The only source is OpenAI’s own report, which says the reviewed results do not show the model obtained the proof’s source code and does not say whether anyone else used the token. A scenario involving a scanner-blocked token in OpenAI’s separate long-horizon post may be related, but neither page links the two.
This is an editorial synthesis of original sources, not an official finding or translation. Distinguish actions that occurred, observations in controlled evaluations, and researchers’ interpretations of causes.
Original sources and follow-ups
Publication order: oldest first- OpenAI