azure-large-instances
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves technical documentation from official Microsoft domains, including learn.microsoft.com and github.com/MicrosoftDocs.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from external documentation sites, which creates a surface for instructions to be processed by the agent. 1. Ingestion points: Documentation URLs from learn.microsoft.com are processed via tools like fetch_webpage. 2. Boundary markers: No explicit delimiters or instructions are provided to the agent to treat fetched content as data only. 3. Capability inventory: The skill uses network access tools to retrieve documentation markdown. 4. Sanitization: No sanitization or validation of the fetched content is described in the skill file.
Audit Metadata