azure-document-intelligence

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a standard reference guide with no executable code or dangerous instructions.
  • [EXTERNAL_DOWNLOADS]: The skill identifies documentation links on learn.microsoft.com. These are used for information retrieval from an official and well-known source.
  • [DATA_EXPOSURE]: No sensitive information, credentials, or private file access was identified in the skill content.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes an attack surface for indirect prompt injection as it ingests content from external URLs listed in SKILL.md. However, the risk is negligible as it targets trusted official documentation and the skill does not possess sensitive capabilities like file-system writes or arbitrary command execution.
  • Ingestion points: Documentation URLs listed in SKILL.md processed via fetch_webpage or mcp_microsoftdocs.
  • Boundary markers: None provided in the prompt templates.
  • Capability inventory: None (the skill only provides documentation).
  • Sanitization: None specified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 03:02 PM