nutrient-document-processing
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill refers to the installation of the
@nutrient-sdk/dws-mcp-serverpackage from the npm registry. This package is the official SDK for Nutrient, which is a well-known document processing service. - [COMMAND_EXECUTION]: The skill uses
curlcommands to interact with the document processing API. These commands handle file uploads and define processing instructions. - [DATA_EXFILTRATION]: User-provided documents are sent to
https://api.nutrient.io/buildfor processing. This is the official endpoint for a well-known service and is the primary intended function of the skill. - [PROMPT_INJECTION]: The skill processes untrusted external data in the form of documents (PDF, DOCX, HTML, images), which creates a surface for indirect prompt injection. Ingestion points: The skill reads and processes files provided by the user. Boundary markers: There are no explicit instructions or delimiters used to ensure the agent ignores instructions potentially embedded within the documents. Capability inventory: The skill can read local files, perform network requests to an external API, and write output files to the local system. Sanitization: No content filtering or sanitization of the processed data is specified.
Audit Metadata