azure-static-web-apps
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and process external content from documentation URLs, which creates a surface for indirect prompt injection if the source content is manipulated.
- Ingestion points: Documentation content is retrieved from multiple
learn.microsoft.comURLs listed in the Category Index using tools likemcp_microsoftdocs:microsoft_docs_fetchorWebFetch. - Boundary markers: No explicit delimiters or instructions are provided to help the agent distinguish between its system instructions and the fetched documentation data.
- Capability inventory: The agent is expected to perform development tasks such as configuring authentication, managing secrets, and handling deployments across Azure services.
- Sanitization: There is no requirement for the agent to sanitize or validate the Markdown content retrieved from the external URLs.
- [EXTERNAL_DOWNLOADS]: The skill is designed to fetch documentation and architectural guidance from official Microsoft domains (
learn.microsoft.com) to assist in development and troubleshooting tasks.
Audit Metadata