git-review
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes git commands (e.g., git diff, git log) using parameters that can be manually defined by the user. If these parameters are not properly sanitized before being passed to the shell, it could lead to command injection.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Because it processes external content (git diffs), malicious instructions hidden within code comments or strings could influence the AI's review or scoring.
- Ingestion points: git diff output (SKILL.md).
- Boundary markers: None present in the system prompt.
- Capability inventory: Shell command execution (git) and local file writing (docs/reviews/).
- Sanitization: No sanitization of the code content or user inputs is described.
Audit Metadata