dual-pass-review

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Indirect Prompt Injection (SAFE): The skill ingests untrusted data in the form of code diffs, which could theoretically contain malicious instructions. However, this is inherent to the code review use-case and the risk is mitigated by the structured checklist approach. \n
  • Ingestion points: Output from git status and git diff commands in Step 1 and Step 5. \n
  • Boundary markers: Absent; the skill does not define specific delimiters for separating the diff content from instructions. \n
  • Capability inventory: Bash, Write, Edit, Grep, Glob, and Task tools. \n
  • Sanitization: Absent; the skill relies on the agent's objective adherence to the provided checklist items.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:43 PM