nutrient-document-processing

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides examples using the curl command to interact with the Nutrient API for document processing tasks such as conversion, OCR, and redaction.
  • [EXTERNAL_DOWNLOADS]: Includes configuration for the @nutrient-sdk/dws-mcp-server package via npx, which is the official tool for this service.
  • [DATA_EXFILTRATION]: Documents are uploaded to the api.nutrient.io endpoint for processing; this is the core function of the skill and involves a well-known service.
  • [PROMPT_INJECTION]: The skill extracts text and data from external documents, which is a vector for indirect prompt injection. Ingestion points: Document content extracted via curl or the MCP server. Boundary markers: None provided in the command examples. Capability inventory: curl commands and npx execution. Sanitization: Extracted document data is processed without specific sanitization or filtering steps described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 09:17 AM