azure-large-instances
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches technical documentation from official Microsoft domains (learn.microsoft.com) to provide up-to-date guidance on Azure Large Instances.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: External documentation is retrieved at runtime from learn.microsoft.com using tools like WebFetch or mcp_microsoftdocs:microsoft_docs_fetch.
- Boundary markers: The skill does not explicitly define delimiters to separate fetched documentation from system instructions.
- Capability inventory: The skill is restricted to informational guidance and does not contain subprocess calls, file-write operations, or other high-risk capabilities.
- Sanitization: The skill relies on the agent's default handling of external content; no specific sanitization of the retrieved markdown is performed within the instructions.
Audit Metadata