code-review-mastery
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to interact with the local git repository and file system.
- Evidence: Runs
git diff --stat,git diff --cached, andlson agent configuration directories to perform reviews and suggest companion skills. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which could contain malicious instructions.
- Ingestion points: Reads output from
git diffand project configuration files (e.g.,README.md,CLAUDE.md,.eslintrc). - Boundary markers: Absent; there are no specific instructions to the agent to disregard instructions embedded within the code being reviewed.
- Capability inventory: Can execute shell commands (
git), read project files, and modify files if the user accepts a "fix" suggestion. - Sanitization: Absent; the skill passes raw diff content directly into the analysis phase.
Audit Metadata