azure-documentdb

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill is designed to fetch documentation content from learn.microsoft.com using the mcp_microsoftdocs tool or a standard web fetcher. These references target a well-known, official service provided by the vendor.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by ingesting and processing data from external URLs.
  • Ingestion points: External documentation content is retrieved via mcp_microsoftdocs:microsoft_docs_fetch and fetch_webpage as described in SKILL.md.
  • Boundary markers: The instructions do not explicitly define boundary markers or delimiters for the fetched content.
  • Capability inventory: The skill provides informational content; the overall risk depends on the execution environment of the agent using the skill.
  • Sanitization: No specific sanitization or validation of the remote Markdown content is defined within the skill itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 01:54 PM