guardrails-reviewer

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely declarative and composed of markdown instructions for the AI agent, containing no executable scripts or system commands.
  • [SAFE]: No hardcoded credentials, sensitive file path references, or unauthorized network communication patterns were identified.
  • [SAFE]: The skill uses localized tools like TodoWrite for progress tracking and AskUserQuestion for interaction, which do not pose a risk of privilege escalation or data exfiltration.
  • [SAFE]: The skill's metadata and descriptions accurately reflect its intended functionality as a documentation reviewer, with no evidence of poisoning or deceptive instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 09:26 PM