azure-document-intelligence
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation from
learn.microsoft.comusing external tools likemcp_microsoftdocs:microsoft_docs_fetchorWebFetch. The destination is an official domain of a well-known service provider, and the fetching is intended for retrieving educational and reference materials. - [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by design, as it ingests content from external web pages. However, the ingestion is targeted at official technical documentation from a reputable service provider, which significantly limits the risk of adversarial content entering the agent context.
Audit Metadata