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
Risk Level
SAFE
Analyzed
Jul 24, 2026, 04:12 PM
Security Audit — agent-trust-hub — pr-review-triage