azure-database-postgresql

Pass

Audited by Gen Agent Trust Hub on Oct 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves documentation from learn.microsoft.com. This is a well-known and trusted service provided by Microsoft.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to ingest and process documentation from external URLs.
  • Ingestion points: Documentation URLs listed in SKILL.md targeting learn.microsoft.com.
  • Boundary markers: The instructions do not specify explicit delimiters or isolation for the external content fetched at runtime.
  • Capability inventory: The skill uses tools like mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage to retrieve content for analysis.
  • Sanitization: There is no mention of specific sanitization, escaping, or filtering of the fetched external documentation before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 26, 2026, 11:38 AM