azure-database-postgresql

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is designed to retrieve external technical documentation from the official learn.microsoft.com domain. It utilizes tools such as mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage to fetch Markdown content from Microsoft-owned infrastructure, which is consistent with the skill's stated purpose and the author's identity.
  • [INDIRECT_PROMPT_INJECTION]: The skill features a documentation-fetching architecture that ingests external data into the agent's context at runtime.
  • Ingestion points: Documentation is pulled from learn.microsoft.com via provided tools and URLs.
  • Boundary markers: Not explicitly defined in the skill instructions.
  • Capability inventory: The agent is restricted to fetching and reading documentation content.
  • Sanitization: No specific content sanitization is described; however, the risk is mitigated by the use of highly trusted, official documentation sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 03:21 PM
Security Audit — agent-trust-hub — azure-database-postgresql