microsoft-docs
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): Comprehensive analysis of the SKILL.md file and referenced tool behaviors confirms that the skill is limited to documentation retrieval and search operations. No unauthorized command execution, persistence mechanisms, or credential theft patterns were found.
- [Indirect Prompt Injection] (SAFE): The skill processes content from external websites, which presents a theoretical surface for indirect prompt injection. However, the risk is mitigated by the use of trusted official domains. 1. Ingestion points: microsoft_docs_fetch, get_doc, and mcp_context7_query-docs. 2. Boundary markers: None explicitly defined in the instructions. 3. Capability inventory: Data retrieval (search and fetch) only; no destructive file system or administrative capabilities are present. 4. Sanitization: Relies on the host AI agent's native safety filters for processing retrieved text.
Audit Metadata