ocr-web-service
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
@membranehq/clito manage authentication (membrane login), create service connections (membrane connect), and execute OCR actions (membrane action run). These commands are standard operations for the Membrane platform. - [EXTERNAL_DOWNLOADS]: The instructions direct the user to install the official CLI tool
@membranehq/clifrom the npm registry. This is a legitimate tool provided by the skill's vendor to facilitate secure API communication. - [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it processes text extracted from external images and documents.
- Ingestion points: Text content extracted from scanned documents, PDFs, and images via the OCR service.
- Boundary markers: Not explicitly defined in the provided skill instructions.
- Capability inventory: Action execution and network operations are mediated through the Membrane CLI and its connected services.
- Sanitization: No explicit sanitization or filtering of the extracted OCR text is described within the skill body.
Audit Metadata