azure-hpc-cache
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references and fetches documentation from learn.microsoft.com. This is an official Microsoft domain and is considered a well-known, trusted source for information.
- [INDIRECT_PROMPT_INJECTION]: The skill functions by ingesting remote documentation which technically creates an attack surface for indirect prompt injection. However, the risk is negligible due to the trusted nature of the source and the lack of dangerous capabilities in the skill itself.
- Ingestion points: Documentation is retrieved from learn.microsoft.com.
- Boundary markers: The instructions do not define specific delimiters for the fetched content.
- Capability inventory: The skill does not perform any high-risk operations such as arbitrary command execution, network exfiltration, or file system writes.
- Sanitization: No sanitization is performed on the incoming documentation text.
Audit Metadata