skill-curator

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes rg (ripgrep) for local searching and gh (GitHub CLI) for retrieving repository information. These are legitimate uses of standard development tools for metadata collection.
  • [EXTERNAL_DOWNLOADS]: The skill fetches repository data and file contents through the official GitHub API and CLI. These network operations target a well-known service and are required for the project evaluation workflow.
  • [PROMPT_INJECTION]: The skill processes untrusted data from external repository README files, creating a surface for indirect prompt injection. However, this risk is inherent to the skill's primary function of content analysis and does not involve the execution of untrusted commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 03:34 PM
Security Audit — agent-trust-hub — skill-curator