code-review
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub pull requests which could contain malicious instructions designed to subvert the code review process.
- Ingestion points: The skill ingests untrusted data including pull request titles, descriptions, and code diffs via
gh pr viewandgh pr diff(Steps 3, 4, and 5 inSKILL.md). - Boundary markers: The instructions do not specify the use of delimiters (e.g., XML tags or triple quotes) or explicit system instructions to ignore embedded commands when passing PR content to sub-agents.
- Capability inventory: The skill has the capability to write to the repository's pull request interface using
gh pr commentandgh pr review(Steps 7 and 9 inSKILL.md). - Sanitization: There is no evidence of sanitization or filtering of the external content before it is interpolated into the prompts for the Haiku, Sonnet, and Opus sub-agents.
Audit Metadata