branch-based-review
Pass
Audited by Gen Agent Trust Hub on May 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill follows a structured auditing process with specific checks for common vulnerabilities like secrets and injection.
- [COMMAND_EXECUTION]: The skill utilizes git and gh CLI tools to obtain the code changes it is asked to review.
- [PROMPT_INJECTION]: The skill ingests untrusted source code and PR descriptions. 1. Ingestion points: Source files and diffs. 2. Boundary markers: Absent. 3. Capability inventory: File system reading and CLI tool execution. 4. Sanitization: None. This attack surface is inherent to the skill's purpose as a code reviewer.
Audit Metadata