codex-review-branch
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes untrusted content from feature branches while possessing broad execution capabilities.
- Ingestion points: Code, diffs, and commit history from the feature branch being reviewed (SKILL.md).
- Boundary markers: Absent; no delimiters or instructions are provided to the agent to disregard commands found within the source code.
- Capability inventory: The agent has access to Bash (including bash:* and git:* patterns), MCP tools (mcp__codex__codex), and file system tools (Read, Grep, Glob).
- Sanitization: There is no evidence of sanitization, escaping, or filtering of the branch content before it is read into the agent's context.
Audit Metadata