apps-connect

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses npx -y theapps-mcp configure to interactively set up the MCP connection. This command is executed in an interactive terminal to ensure user-entered credentials do not flow through the AI agent's chat history or logs.
  • [EXTERNAL_DOWNLOADS]: The use of npx triggers a download of the theapps-mcp package from the public NPM registry. This package is the official tool for the service provided by the vendor.
  • [SAFE]: The instructions explicitly forbid the agent from requesting, repeating, or printing sensitive credentials (App ID, App Secret, Access Tokens) in chat, files, logs, or command arguments. It also directs the agent to only enable write operations if explicitly required by the user via an environment variable.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 11:41 AM