azure-dedicated-hsm
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves technical documentation from
learn.microsoft.comusing themcp_microsoftdocstool or standard web fetching. These sources are official vendor-controlled endpoints. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external URLs, creating a theoretical attack surface for indirect prompt injection.
- Ingestion points: Documentation fetched from
learn.microsoft.comURLs listed in the Category Index. - Boundary markers: Absent; no specific delimiters or ignore instructions are provided for fetched content.
- Capability inventory: The skill does not possess dangerous tools or capabilities such as file system writes, arbitrary command execution, or network exfiltration.
- Sanitization: Content is retrieved and processed as Markdown without sanitization for embedded instructions.
Audit Metadata