azure-resource-manager
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to fetch remote Markdown content using
mcp_microsoftdocs:microsoft_docs_fetchorfetch_webpagefrom external URLs. This represents an indirect prompt injection surface where instructions embedded in the fetched data could influence the agent's behavior. - Ingestion points: Documentation is dynamically fetched from URLs under
learn.microsoft.comas defined in the Troubleshooting, Best Practices, and other category tables inSKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions to treat the fetched content as untrusted data.
- Capability inventory: The skill utilizes network-enabled tools (
microsoft_docs_fetch,fetch_webpage) and local file reading (read_file). - Sanitization: There is no evidence of content sanitization or validation before the fetched data is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill is designed to fetch documentation and guidelines from
learn.microsoft.com. This is a well-known service provided by a trusted organization.
Audit Metadata