code-review
Pass
Audited by Gen Agent Trust Hub on Aug 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses local shell commands via
git(specificallygit diff,git log, andgit rev-parse) to retrieve source code changes and commit history for analysis. - [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) because it ingests untrusted data from the repository's git history and source files.
- Ingestion points: Data enters the agent context through
git diffoutput,git logcommit messages, and external specification files (PRDs/Issues). - Boundary markers: The instructions do not define clear delimiters or "ignore embedded instructions" warnings when passing this untrusted data to the sub-agents.
- Capability inventory: The skill can execute shell commands (
git), read local files, and spawn sub-agents with general-purpose capabilities. - Sanitization: There is no mention of sanitizing or escaping the diff content or commit messages before they are interpolated into the sub-agent prompts.
Audit Metadata