azure-api-center
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an installation guide for the
mcp_microsoftdocstool hosted on the MicrosoftDocs official GitHub repository. This is a reference to a trusted vendor's resource and is used for its intended primary purpose. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data by fetching documentation from
learn.microsoft.com. This creates an inherent surface for indirect prompt injection where third-party content could theoretically contain instructions to influence the agent. - Ingestion points: External documentation is retrieved via the
mcp_microsoftdocs:microsoft_docs_fetchandfetch_webpagetools as instructed inSKILL.md. - Boundary markers: The skill does not explicitly define delimiters or specific "ignore" instructions for the fetched content.
- Capability inventory: The skill utilizes file reading and network fetching capabilities to provide documentation to the agent.
- Sanitization: No explicit sanitization or schema validation is performed on the Markdown content retrieved from the external documentation service.
Audit Metadata