browse-and-evaluate

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for executing the ai-agent-skills CLI tool via npx to search for and manage other skills.
  • [EXTERNAL_DOWNLOADS]: The workflow involves fetching metadata and skill definitions from external sources during the catalog browsing and installation phases.
  • [SAFE]: The skill incorporates security guardrails by instructing the agent to use a preview command that sanitizes content for prompt injection and to perform dry-runs before any installation, mitigating risks from untrusted external data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 04:17 PM