pr-review-triage
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: No security threats or malicious behaviors were detected in the skill definitions.
- [NO_CODE]: The skill is comprised entirely of natural language instructions and contains no scripts, binaries, or automated tasks.
- [PROMPT_INJECTION]: The skill processes external data from pull requests, which constitutes an indirect prompt injection surface. Ingestion points: Pull Request metadata, including titles, comments, and labels (SKILL.md). Boundary markers: None explicitly defined to separate untrusted PR content from instructions. Capability inventory: None; the skill is limited to generating reports and does not execute commands or network requests. Sanitization: None specified for ingested PR data. Assessment: The risk is negligible because the output is restricted to informational reports without execution side effects.
Audit Metadata