discover-azure-skills

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • External Resource Access: The skill retrieves catalog metadata and skill descriptions from Microsoft's official GitHub repository (github.com/microsoft/azure-skills). This is an expected behavior for a discovery tool and uses the vendor's own infrastructure.
  • Dynamic Skill Installation: The skill provides instructions for installing additional plugins using platform-specific commands (such as npx skills add or /plugin install). These commands target the vendor's repository to extend the agent's capabilities as requested by the user.
  • Data Ingestion Surface: The skill reads remote markdown files to present skill descriptions to the user. This involves processing external content, which is a necessary component of the skill's discovery functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 04:39 PM
Security Audit — agent-trust-hub — discover-azure-skills