code-review-excellence
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data in the form of pull request code and descriptions. While the skill contains security checklists to identify vulnerabilities in the code being reviewed, a malicious PR could contain prompt injection attacks designed to influence the agent's behavior or output during the review process.
- Ingestion points: PR descriptions and source code files.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the code being analyzed.
- Capability inventory: The skill references a script
scripts/pr-analyzer.pyfor complexity analysis and suggests the use of standard development tools, though no dangerous capabilities are directly invoked within the SKILL.md body. - Sanitization: No explicit sanitization or filtering of the external code input is described in the provided instructions.
Audit Metadata