azure-table-storage
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources (learn.microsoft.com) via documentation fetching tools. This creates an indirect prompt injection surface where instructions embedded in the external content could potentially influence the agent's behavior.
- Ingestion points: External URLs retrieved via
mcp_microsoftdocs:microsoft_docs_fetchandfetch_webpageinSKILL.md. - Boundary markers: None identified in the prompt templates.
- Capability inventory: Uses tool calls for fetching documentation.
- Sanitization: Not present; the skill retrieves and processes Markdown content directly.
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from Microsoft's official domains (learn.microsoft.com) and references an installation guide on GitHub (
github.com/MicrosoftDocs/mcp). These network operations are intended for documentation retrieval from vendor-controlled resources.
Audit Metadata