azure-quantum

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a structured directory of links to official Azure Quantum documentation. No malicious patterns, obfuscation, or unauthorized operations were identified.
  • [EXTERNAL_DOWNLOADS]: The skill specifies the use of documentation-fetching tools to retrieve technical content from learn.microsoft.com. These references target official vendor infrastructure and are appropriate for the skill's function.
  • [PROMPT_INJECTION]: Instructional notes for the agent are confined to operational guidance regarding file reading and tool selection, presenting no attempt to bypass safety constraints.
  • [PROMPT_INJECTION]: Evaluation of indirect prompt injection surface: (1) Ingestion points: Fetches remote documentation via tool calls (microsoft_docs_fetch, fetch_webpage). (2) Boundary markers: Not explicitly defined in the skill content. (3) Capability inventory: The skill does not implement any high-risk capabilities such as command execution or file system modification. (4) Sanitization: The skill relies on retrieving content from highly trusted, official Microsoft sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:42 AM