azure-service-health
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches remote technical documentation from the official
learn.microsoft.comdomain using themicrosoft_docs_fetchandfetch_webpagetools. \n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external URLs which represents a potential injection surface. \n - Ingestion points: Documentation content fetched dynamically from Microsoft Learn as described in
SKILL.md. \n - Boundary markers: The prompt instructions do not provide explicit delimiters to isolate the fetched external content. \n
- Capability inventory: The agent uses networking capabilities to retrieve and process documentation. \n
- Sanitization: Fetched Markdown content is not explicitly sanitized or filtered before processing. \n- [EXTERNAL_DOWNLOADS]: References the official
MicrosoftDocsGitHub repository for tool installation and documentation updates.
Audit Metadata