azure-quantum
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation content from official domains such as
learn.microsoft.com. These references target official technical documentation and are handled via documented tools, representing standard and expected behavior for a reference-based skill. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process remote content, which inherently creates a surface for indirect prompt injection.
- Ingestion points: Remote documentation is fetched at runtime from the
learn.microsoft.comdomain usingmicrosoft_docs_fetchorfetch_webpage. - Boundary markers: No specific boundary markers or instructions to ignore embedded commands are defined in the skill instructions.
- Capability inventory: The skill contains no executable capabilities such as file system write access, arbitrary command execution, or data exfiltration routines.
- Sanitization: The skill relies on the agent's default handling of fetched Markdown content without implementing additional sanitization or validation steps.
Audit Metadata