Now in research preview: Codex Security Review It takes a deeper look at GitHub
Source
OpenAIDevs
Author
OpenAIDevs
Date
Terms in this piece · Glossary
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
Why it matters
An AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → that reviews PRs for security using repo context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → is a directly adoptable addition to a team's existing review pipeline.
Key quotes
“During the introductory period, Codex Security Review does
not consume ChatGPT credits.”
OpenAIDevs
“Codex Security Review goes deeper than Code
Review on security-specific risks by analyzing the
pull request diff, supporting repository context, and configured threat models
or security guidance.”
OpenAIDevs
“By default, automatic Codex Security Reviews report High and Critical
findings, while manually requested reviews report Medium , High , and
Critical findings.”
OpenAIDevs
“If you do not specify a source, Codex regenerates the
threat model for every review.”
