nutrient-openclaw
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted documents from chat attachments or workspace files for OCR, extraction, and redaction, creating a surface for indirect prompt injection.
- Ingestion points: The
nutrient_extract_text,nutrient_ocr, andnutrient_ai_redacttools ingest external file content into the agent context. - Boundary markers: The instructions do not specify the use of clear delimiters or instructions to the agent to ignore potential commands embedded within the processed document text.
- Capability inventory: The skill utilizes network capabilities to send data to Nutrient DWS and file system capabilities to write transformed output files.
- Sanitization: No explicit sanitization, filtering, or validation of the extracted document content is described in the skill workflow.
- [EXTERNAL_DOWNLOADS]: The skill installs and utilizes a Node.js package from an external registry.
- Evidence: The skill instructs the installation of
@nutrient-sdk/nutrient-openclawfrom npm. - Source: The package is associated with the official repository at
https://github.com/PSPDFKit-labs/nutrient-openclawand the service athttps://www.nutrient.io/.
Audit Metadata