code-review-excellence
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to analyze untrusted external data in the form of pull requests and code changes, creating a surface for indirect prompt injection where malicious instructions could be embedded in the reviewed content.
- Ingestion points: Pull request descriptions and code changes as identified in the skill's description and 'When to Use' sections.
- Boundary markers: The guidelines do not specify delimiters or 'ignore' instructions to isolate the untrusted content of the pull request from the agent's logic.
- Capability inventory: The skill references a local script 'scripts/pr-analyzer.py' (not provided) and provides templates for generating structured feedback comments.
- Sanitization: No specific sanitization or escaping mechanisms are described to mitigate risks from malicious code comments or documentation found in pull requests.
Audit Metadata