guardskills

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the guardskills package from the npm registry, which is a well-known service.
  • [REMOTE_CODE_EXECUTION]: It uses npx to download and run the guardskills scanner, which is a documented and intended behavior for this utility.
  • [COMMAND_EXECUTION]: The skill executes shell commands to interface with external skill installers like skills.sh, playbooks, and skillkit after completing its security scan.
  • [PROMPT_INJECTION]: As a security scanner, the tool processes untrusted data from external repositories. While this creates a surface for indirect prompt injection, the skill includes a specific rule matrix to detect and block such patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 05:29 PM