azure-ai-document-intelligence-ts
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install official packages from Microsoft's Azure organization (@azure-rest/ai-document-intelligence and @azure/identity) via the NPM registry.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection by ingesting and processing content from external document URLs and local files. Ingestion points: Untrusted data enters the agent context through the urlSource and base64Source parameters in analyze operations (SKILL.md). Boundary markers: Absent; there are no specific delimiters or instructions provided to the agent to disregard potentially malicious text embedded within processed documents. Capability inventory: The skill performs network operations to official Azure endpoints and reads local files via node:fs/promises. Sanitization: Absent; the skill extracts and logs raw content from documents without validation or filtering.
Audit Metadata