The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches and executes the @nutrient-sdk/dws-mcp-server package from NPM using npx. This is an official integration tool provided by the service vendor for Model Context Protocol support.
[COMMAND_EXECUTION]: Uses curl to interact with the Nutrient API for processing documents. This involves reading local files and writing the processed results back to disk as part of the intended workflow.
[DATA_EXFILTRATION]: Transmits document content to the api.nutrient.io domain for processing. While this involves sending data to a remote endpoint, it is the primary function of the skill and targets the official infrastructure of a well-known service provider.
[PROMPT_INJECTION]: The skill processes external data (PDFs, images, DOCX) which serves as a surface for indirect prompt injection (Category 8). Instructions hidden within processed documents could potentially influence agent behavior.
Ingestion points: Documents uploaded via curl in SKILL.md.
Boundary markers: Absent; the skill does not wrap document content in specific delimiters.
Capability inventory: Includes network access (via curl) and local file system access (read/write).
Sanitization: No content sanitization or instruction-filtering is applied to the documents before they are processed.

nutrient-document-processing