pr-review-static

Pass

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to provide structured guidance for code reviews. It includes proactive security checks, such as identifying hardcoded tokens or secrets in documentation files (Checklist Item 20).
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and analyze untrusted data (code diffs from a repository). However, the risk is negligible as the skill only performs read operations for context and does not have the capability to execute the code it reviews or perform network exfiltration.
  • Ingestion points: Code diffs accessed via git diff (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: Read-only command execution for Git diffs; no file-write or network capabilities detected.
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 25, 2026, 01:22 PM
Security Audit — agent-trust-hub — pr-review-static