code-review

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by analyzing codebases. A malicious file within the scope could contain instructions designed to influence the agent's behavior during the review process.
  • Ingestion points: Workflow step 'Analyze Every In-Scope File' in SKILL.md.
  • Boundary markers: The instructions lack specific delimiters or warnings to ignore instructions embedded within the code files.
  • Capability inventory: All scripts (SKILL.md) request read-only access; the skill explicitly forbids file modifications, creation, or deletion.
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 10:30 AM
Security Audit — agent-trust-hub — code-review