ocr-and-documents

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches machine learning models from HuggingFace to support OCR and layout analysis through the marker-pdf library. This is a standard operation for the tool's functionality.- [COMMAND_EXECUTION]: Includes Python scripts that wrap document parsing libraries. These scripts take local file paths as arguments for processing.- [PROMPT_INJECTION]: The skill facilitates the ingestion of external data from various document formats into the agent context. This establishes an indirect prompt injection surface, which is managed by the agent's core safety layers and is intrinsic to document analysis tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 06:29 PM