nutrient-document-processing

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates processing and extracting data from external documents (PDF, DOCX, HTML, images). This creates a surface for indirect prompt injection where instructions hidden within a document could influence the agent's behavior. \n
  • Ingestion points: Document content extracted via the Nutrient API (e.g., text extraction, OCR). \n
  • Boundary markers: None identified in the provided command examples. \n
  • Capability inventory: Executes curl for API interaction and npx for the MCP server. \n
  • Sanitization: No specific sanitization or filtering of extracted content is described.\n- [COMMAND_EXECUTION]: The skill utilizes curl commands to interact with the Nutrient API, sending local documents for remote processing.\n- [EXTERNAL_DOWNLOADS]: The skill suggests running the @nutrient-sdk/dws-mcp-server package via npx, which downloads code from the npm registry at runtime. This targets an official package from a well-known service provider.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 07:42 AM
Security Audit — agent-trust-hub — nutrient-document-processing