review-gate

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security vulnerabilities, malicious patterns, or dangerous commands were detected. The skill is composed entirely of markdown instructions and reference checklists for manual or AI-assisted code review.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data, which is an inherent part of code review tasks.
  • Ingestion points: The instructions direct the agent to read pull request diffs, linked issues, and output from external automated review tools (SKILL.md).
  • Boundary markers: No specific delimiters are defined to separate untrusted code/comments from the agent's instructions.
  • Capability inventory: The skill only involves reading content and generating a review report; it does not authorize file writes, network exfiltration, or shell command execution.
  • Sanitization: The instructions do not specify any sanitization or filtering for the data being reviewed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 05:53 AM
Security Audit — agent-trust-hub — review-gate