azure-app-testing
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves Markdown documentation from
learn.microsoft.comusing tools likemicrosoft_docs_fetchandfetch_webpage. These are official Microsoft domains and represent intended functionality for this expert knowledge skill. - [INDIRECT_PROMPT_INJECTION]: The skill incorporates external content into the agent's context, which presents a surface for indirect prompt injection.
- Ingestion points: Documentation content is fetched from remote URLs under
learn.microsoft.comas described inSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or clear "ignore embedded instructions" warnings when processing the fetched documentation content.
- Capability inventory: The skill is informational and provides guidance; it does not explicitly invoke dangerous tools but provides the agent with context to perform development tasks.
- Sanitization: No explicit sanitization or validation of the fetched Markdown content is defined in the skill instructions.
Audit Metadata