chaindesk

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the official Membrane CLI package @membranehq/cli from the NPM registry. This tool is provided by the skill's author to handle authentication and manage API interactions.
  • [COMMAND_EXECUTION]: The skill utilizes the membrane command-line interface to perform various operations, including authentication (membrane login), connection management (membrane connect), and executing specific Chaindesk actions (membrane action run). These commands are standard for the intended integration logic.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes actions that ingest untrusted data from external sources, such as retrieving conversation messages (get-conversation-messages) and querying datastores (query-datastore). While this creates a surface for potential indirect prompt injection from customer messages, it is a primary and expected function of a support platform integration.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 11:21 PM
Security Audit — agent-trust-hub — chaindesk