nutrient-document-processing
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill extracts text and data from external documents, which creates a surface for indirect prompt injection where hidden instructions in a document could manipulate the agent's behavior.
- Ingestion points: Document files in formats like PDF, DOCX, and HTML are processed in
SKILL.mdusingcurlcommands. - Boundary markers: There are no instructions or delimiters provided to help the agent distinguish between its own system prompt and content found within the documents.
- Capability inventory: The skill has the capability to perform network requests and write files to the local file system.
- Sanitization: No sanitization or validation of the extracted document content is performed.
- [EXTERNAL_DOWNLOADS]: Recommends the installation of the
@nutrient-sdk/dws-mcp-serverpackage vianpx, which involves downloading and executing code from the NPM registry. - [DATA_EXFILTRATION]: Transmits document data to the external Nutrient DWS API at
api.nutrient.io. While this is required for the document processing functionality, it involves transferring potentially sensitive information to a third-party cloud service.
Audit Metadata