pr-code-review
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from pull request descriptions, issue bodies, and linked tickets during its analysis phase. This input could potentially contain malicious instructions intended to subvert the review process or bias the agent's conclusions.
- Ingestion points: Pull request descriptions, issue bodies, and linked tickets (SKILL.md, step 4).
- Boundary markers: No explicit delimiters or boundary markers are defined to isolate untrusted external content from the agent's internal instructions.
- Capability inventory: The skill maintains the ability to post comments and reviews to external hosting platforms via the gh and glab CLI tools (SKILL.md, step 11).
- Sanitization: There is no evidence of sanitization or validation of the text retrieved from external sources before it influences the agent's output.
- [COMMAND_EXECUTION]: The skill utilizes the gh (GitHub) and glab (GitLab) command-line interfaces to perform repository operations, including resolving commit references and publishing review feedback (SKILL.md, steps 3 and 11).
Audit Metadata