code-review
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates as a code review tool, analyzing repository content via git and GitHub CLI commands, which is appropriate for its stated purpose.
- [COMMAND_EXECUTION]: The skill suggests running
python3 scripts/smart_commit_analyzer.pyfor regression checks. This script is expected to be part of the local project repository. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted code changes from git diffs and files. 1. Ingestion points: Data enters the context via
git diff,gh pr diff, and file reading. 2. Boundary markers: The instructions do not specify delimiters to isolate code content from the agent's instructions. 3. Capability inventory: The skill is capable of reading repository data and executing a local script, but lacks network exfiltration capabilities. 4. Sanitization: No sanitization of the input code is performed before processing.
Audit Metadata