azure-repos
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill is designed to fetch content from external URLs to provide documentation. Specifically, it uses tools to retrieve data from learn.microsoft.com, which is a well-known, official service for Microsoft documentation. This activity is consistent with the skill's primary purpose.
- [REMOTE_CODE_EXECUTION]: The skill provides a link to an installation guide for the 'mcp_microsoftdocs' tool on GitHub. The link points to the official MicrosoftDocs organization, which is a trusted source.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection because it ingests data from external websites.
- Ingestion points: The skill utilizes 'mcp_microsoftdocs:microsoft_docs_fetch' and 'fetch_webpage' to pull content from learn.microsoft.com (SKILL.md).
- Boundary markers: The skill does not explicitly define delimiters or instructions to ignore embedded commands within the fetched content.
- Capability inventory: The agent is instructed to use 'read_file' to access parts of the skill index (SKILL.md).
- Sanitization: No specific sanitization or filtering logic is provided for the fetched documentation.
- Context: The risk is negligible as the ingestion points are restricted to official Microsoft documentation sites, which are highly trusted origins.
Audit Metadata