azure-ai-document-intelligence-ts

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of @azure-rest/ai-document-intelligence and @azure/identity from the official npm registry. These are well-known, official libraries maintained by Microsoft Azure.
  • [DATA_EXFILTRATION]: The skill transmits document content to Azure Cognitive Services endpoints (e.g., cognitiveservices.azure.com) for analysis. This is documented as the primary function of the skill and utilizes well-known service infrastructure.
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection (Category 8) by design.
  • Ingestion points: The skill ingests untrusted data from external sources via the urlSource and base64Source parameters in SKILL.md.
  • Boundary markers: The provided code examples do not demonstrate the use of delimiters or specific instructions to the agent to ignore potentially malicious commands embedded within the documents being analyzed.
  • Capability inventory: The skill possesses the capability to read local files (via readFile), write files (via writeFile in the acceptance criteria), and perform network communication with Azure APIs.
  • Sanitization: There is no evidence of sanitization or filtering applied to the text extracted by the service (e.g., result.analyzeResult?.content) before it is returned to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 12:35 AM