code-quality
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
git diffandgit diff --cachedcommands to retrieve source code changes for analysis. These commands are necessary for the skill's core functionality as a pre-commit review tool. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests untrusted code content that could contain instructions hidden in comments.
- Ingestion points: Local source code files and git history (Step 2: Analyze Code).
- Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands within the code being analyzed.
- Capability inventory: Includes the ability to read local files and execute git shell commands.
- Sanitization: None; the skill processes code contents directly without filtering or validation.
Audit Metadata