microsoft-foundry-tools
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from official Microsoft domains (learn.microsoft.com) using mcp_microsoftdocs:microsoft_docs_fetch and WebFetch.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external URLs, representing an attack surface for indirect prompt injection.
- Ingestion points: External documentation fetched from learn.microsoft.com URLs using mcp_microsoftdocs:microsoft_docs_fetch or WebFetch.
- Boundary markers: None explicitly defined for the fetched content in the skill instructions.
- Capability inventory: No dangerous operations such as file-writing, subprocess execution, or arbitrary network exfiltration were identified.
- Sanitization: Content is fetched from a trusted vendor portal.
Audit Metadata