azure-document-intelligence
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches technical documentation from Microsoft's official technical domain (learn.microsoft.com) and references the MicrosoftDocs GitHub repository for tool installation instructions. These are well-known and trusted vendor resources.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content from remote documentation sources, creating a potential surface for indirect prompt injection.\n
- Ingestion points: Technical documentation is fetched using the
mcp_microsoftdocs:microsoft_docs_fetchandfetch_webpagetools as described in the compatibility section ofSKILL.md.\n - Boundary markers: The skill instructions do not specify any delimiters or boundary markers to separate the fetched content from the agent's core instructions.\n
- Capability inventory: The skill is strictly limited to information retrieval; it contains no definitions for high-risk capabilities such as arbitrary command execution, file system modification, or network exfiltration of local data.\n
- Sanitization: No explicit sanitization, validation, or filtering mechanisms are defined for the fetched Markdown content within the skill's instructions.
Audit Metadata