document-extraction-api
Pass
Audited by Gen Agent Trust Hub on Jun 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes the
nutrient-dwsPython package, which is the official SDK for the Nutrient service managed by PSPDFKit. - [DATA_EXFILTRATION]: The skill transmits the content of local documents to the Nutrient API (api.nutrient.io) for parsing. This network operation is the intended primary function of the skill and targets the vendor's official endpoint.
- [COMMAND_EXECUTION]: The
scripts/parse.pyscript accepts and processes user-supplied command-line arguments for input and output file paths. - [PROMPT_INJECTION]: The skill possesses a surface for 'Indirect Prompt Injection' because it processes untrusted documents and returns their content to the agent for downstream tasks like RAG ingestion.
- Ingestion points:
scripts/parse.pyreads user-provided files (PDF, images, Office documents) to send them to the extraction API. - Boundary markers: The skill does not implement or instruct the use of delimiters to wrap the extracted Markdown or JSON content.
- Capability inventory: The skill has network access (to the Nutrient API) and file system write access (to save results).
- Sanitization: The skill does not perform sanitization, escaping, or validation of the extracted document content before returning it to the agent context.
Audit Metadata