azure-netapp-files
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses tools to fetch technical documentation from
learn.microsoft.com. These references target a well-known and trusted technology service provider and are used to provide the agent with up-to-date context on Azure services. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests content from external documentation pages.
- Ingestion points: Numerous URLs pointing to Microsoft Azure documentation are processed via
WebFetchor themicrosoft_docs_fetchtool. - Boundary markers: The skill does not explicitly define markers to encapsulate the fetched content or warn the agent to ignore instructions embedded within the documentation.
- Capability inventory: The skill logic is limited to reading documentation and does not include risky capabilities like shell execution, file system writes, or sensitive data exfiltration.
- Sanitization: Content is retrieved from a trusted source and processed as technical reference material.
Audit Metadata