review
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository being reviewed.\n
- Ingestion points: The skill reads output from
git diffandgit logcommands, as well as the contents of specification files located indocs/,specs/, or.scratch/(SKILL.md).\n - Boundary markers: The prompts constructed for the sub-agents do not include explicit instructions to ignore or delimit potentially malicious instructions embedded within the code diffs or spec files.\n
- Capability inventory: The skill invokes git commands and spawns parallel sub-agents; it does not perform direct network operations or file-system writes beyond standard agent capabilities.\n
- Sanitization: No explicit sanitization or validation of the diff output or spec content is performed before passing it to sub-agents.\n- [COMMAND_EXECUTION]: The skill utilizes git commands, including
git diff,git log, andgit rev-parse, to analyze the repository state. These commands are restricted to the local repository and are used for their intended purpose in a code review workflow.
Audit Metadata