dotnet-managedcode-markitdown
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill provides high-level design patterns for document processing pipelines.
- [PROMPT_INJECTION]: The skill describes a workflow for ingesting untrusted data (external documents) for AI workflows (indirect prompt injection surface).
- Ingestion points: Document sources handled by the application (SKILL.md).
- Boundary markers: Not specified in the guidance.
- Capability inventory: No active code, subprocess calls, or network operations are included in the skill files.
- Sanitization: The guidance does not specify sanitization or validation methods for converted content prior to AI ingestion.
Audit Metadata