nutrient-document-processing

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The required workflow sends user-provided documents (e.g., PDFs/images/HTML) to an external processor API for text/OCR extraction, so any outsider-authored content inside those documents can be converted into readable text and returned/ingested into the agent’s LLM context (indirect prompt injection risk).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The MCP server configuration runs "npx -y @nutrient-sdk/dws-mcp-server", which will fetch and execute remote code from the npm package page https://www.npmjs.com/package/@nutrient-sdk/dws-mcp-server at runtime, creating a direct execution dependency.