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/cli to 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/cli from 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
Risk Level
SAFE
Analyzed
May 1, 2026, 11:50 PM
Security Audit — agent-trust-hub — ocr-web-service