skill-discovery

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and execute the skills@1.5.23 package. This package is maintained by a well-known service provider, and the skill documentation explicitly links to their public repository for transparency.
  • [COMMAND_EXECUTION]: The skill utilizes a PowerShell wrapper script to invoke the discovery tool. It includes an example command using -ExecutionPolicy Bypass, which is a common requirement for executing local automation scripts in Windows environments without modifying global system policies.
  • [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface by ingesting search results from a public catalog. However, it mitigates this risk by providing strict procedural requirements for the agent: it must verify licenses, hashes, and runtime requirements, and perform isolated testing before any adoption, preventing the automatic execution of untrusted instructions found in search results.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 12:46 AM