azure-static-web-apps
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 documentation from official Microsoft domains (learn.microsoft.com). These external references are appropriate for the skill's primary purpose and originate from a trusted vendor environment.
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it ingests and processes remote markdown content from documentation pages.
- Ingestion points: Documentation pages from learn.microsoft.com are fetched using mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage.
- Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for the remote content.
- Capability inventory: The skill uses content fetching tools to retrieve markdown but does not invoke shell commands or write to the filesystem using the fetched data.
- Sanitization: No explicit sanitization or filtering of the retrieved remote content is performed before interpolation into the agent context.
- [SAFE]: No evidence of malicious behavior, obfuscation, or unauthorized access was found. The skill follows standard documentation assistance patterns using resources owned by the author.
Audit Metadata