review-guidelines

Pass

Audited by Gen Agent Trust Hub on May 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of static markdown-based instructions for code quality, testing, and Bun runtime conventions. It contains no scripts, binaries, or executable commands.
  • [SAFE]: No network operations, data exfiltration patterns, or external downloads were detected.
  • [SAFE]: The skill is intended to process code from Pull Requests, which constitutes a surface for indirect prompt injection. However, the skill has no functional capabilities to exploit. Ingestion points: Pull Request code and diffs (referenced in description); Boundary markers: Absent; Capability inventory: None detected; Sanitization: Absent.
  • [SAFE]: The guidelines explicitly instruct the agent to check for security issues, such as command injection, XSS, and hardcoded secrets, in the code it reviews.
Audit Metadata
Risk Level
SAFE
Analyzed
May 28, 2026, 07:05 AM
Security Audit — agent-trust-hub — review-guidelines