ss-code-review
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local CLI tools to fetch context and code diffs.
- Evidence: Uses
git diff,git log,gh pr diff,gh pr view,glab mr diff, andglab mr viewto gather data for analysis. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via untrusted data in code diffs or pull request descriptions.
- Ingestion points: Code changes fetched via
git diffand pull request metadata fromghorglabare interpolated into subagent prompts. - Boundary markers: Employs markdown headers (e.g.,
## Diff,## PR Context) to delineate external data from subagent instructions. - Capability inventory: Performs subprocess calls to
git,gh, andglabin SKILL.md. - Sanitization: No explicit sanitization or escaping of external content before interpolation is described.
Audit Metadata