azure-resiliency
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 content from
learn.microsoft.comusingmicrosoft_docs_fetchorfetch_webpage. These operations are used to provide the agent with up-to-date documentation from the vendor's official resources. - [INDIRECT_PROMPT_INJECTION]: The skill interacts with external web content, which presents a surface for indirect prompt injection.
- Ingestion points: Data is ingested from official Microsoft documentation URLs (learn.microsoft.com) as specified in the Category Index.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the fetched content as untrusted data.
- Capability inventory: The skill utilizes tools for fetching and reading text-based documentation.
- Sanitization: The skill relies on the inherent trust of the vendor's documentation platform and does not implement independent sanitization of the retrieved Markdown.
Audit Metadata