nutrient-document-processing
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches and executes the
@nutrient-sdk/dws-mcp-serverpackage from the npm registry usingnpxto provide native tool integration for the agent. - [INDIRECT_PROMPT_INJECTION]: The skill processes external documents, creating a potential surface for indirect prompt injection if the documents contain malicious instructions.
- Ingestion points: Documents in various formats (PDF, DOCX, etc.) are uploaded to the Nutrient API for processing and text extraction.
- Boundary markers: Absent; the skill does not define specific delimiters or instructions for the agent to ignore content within the processed documents.
- Capability inventory: The skill can read local files, write output files, and perform network requests to api.nutrient.io.
- Sanitization: Absent; the raw extracted text and data are returned for agent consumption.
Audit Metadata