code-review-excellence
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted data in the form of pull requests and code changes. This creates an attack surface where malicious instructions could be embedded in the code being reviewed to influence the agent's behavior.
- Ingestion points: The skill instructions specifically direct the agent to read pull request descriptions, linked issues, and code changes (
SKILL.mdandresources/implementation-playbook.md). - Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between the data it is analyzing and its own instructions, nor are there warnings to ignore instructions embedded in the code under review.
- Capability inventory: The skill is primarily focused on analysis and feedback generation. While it mentions a script (
scripts/pr-analyzer.py), it does not explicitly command the agent to execute code, perform network operations, or write to the file system. - Sanitization: No sanitization, escaping, or filtering of the external code content is defined in the instructions.
Audit Metadata