skills/agentskill-sh/learn/learn/Gen Agent Trust Hub

learn

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill communicates with the vendor's official API to perform search, installation, and version checking operations.
  • Evidence: Network requests made via WebFetch to https://agentskill.sh/api/agent/search, https://agentskill.sh/api/agent/skills/<slug>/install, and https://agentskill.sh/api/agent/skills/learn/version.
  • [COMMAND_EXECUTION]: Executes local shell commands to analyze the user's project environment and determine correct installation paths for various agent platforms.
  • Evidence: Commands such as git branch --show-current are used to provide context-aware skill recommendations, and mkdir -p is used to manage skill directories.
  • [REMOTE_CODE_EXECUTION]: Provides a mechanism to download and install new agent instructions (skills) from the remote registry. This behavior is mitigated by an integrated security scanning system.
  • Evidence: The 'Install Flow' logic fetches remote content and writes it to the local filesystem only after performing a security scan that blocks content with low security scores (below 70/100).
  • [SAFE]: The skill includes a 'Self-Update' feature and an opt-out automatic rating system, both of which are transparently documented and aligned with the tool's purpose as a maintenance and discovery utility.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 08:14 AM