azure-oracle
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves technical documentation from the official Microsoft Learn domain (learn.microsoft.com) using dedicated tools like
microsoft_docs_fetch. - [EXTERNAL_DOWNLOADS]: Recommends the installation of the
mcp_microsoftdocstool from the official MicrosoftDocs GitHub repository (github.com/MicrosoftDocs/mcp). - [PROMPT_INJECTION]: Contains instructions for the AI agent to handle fallbacks between documentation tools and check for skill updates based on metadata age. These are natural instructional directives for correct operation.
- [INDIRECT_PROMPT_INJECTION]: The skill processes content fetched from external documentation URLs, which creates a potential surface for instructions embedded in documentation to influence the agent.
- Ingestion points: Content fetched from learn.microsoft.com (SKILL.md).
- Boundary markers: None identified.
- Capability inventory: Functionality is focused on documentation retrieval and display.
- Sanitization: No explicit sanitization or filtering of the fetched Markdown content is specified.
Audit Metadata