erpnext

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli tool from the official npm registry. This package is the standard interface for the Membrane platform, which is the vendor of this skill.
  • [COMMAND_EXECUTION]: Uses the membrane CLI to perform administrative and data tasks. Authentication is handled through a secure browser-based login flow (membrane login), ensuring that sensitive credentials are not stored locally or handled directly by the AI agent.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its primary function of processing external data from ERPNext.
  • Ingestion points: Data retrieved via document listing and retrieval actions (e.g., Customers, Leads, Sales Orders).
  • Boundary markers: Not present in the instruction templates.
  • Capability inventory: The skill can modify data in ERPNext using membrane action run and membrane request.
  • Sanitization: Not specified in the provided markdown instructions.
  • [SAFE]: No malicious intent, obfuscation, or unauthorized access patterns were detected. The skill explicitly promotes secure practices, such as avoiding manual handling of API keys.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 03:02 PM