azure-microsoft-discovery

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches documentation content from official Microsoft domains (learn.microsoft.com). These are recognized as trusted and well-known services.
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external content, creating a potential surface for indirect prompt injection vulnerabilities.
  • Ingestion points: Data is ingested via the mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage tools as specified in the compatibility and usage sections of SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or "ignore" instructions to separate external data from the agent's core instructions.
  • Capability inventory: The skill uses network tools to fetch and process markdown documentation from external URLs.
  • Sanitization: No explicit sanitization, filtering, or validation of the retrieved documentation content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 03:21 PM
Security Audit — agent-trust-hub — azure-microsoft-discovery