chatwork

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the NPM registry. This is a legitimate tool provided by the vendor (membrane) to facilitate the integration.
  • [COMMAND_EXECUTION]: The instructions involve running the membrane command-line utility to handle authentication, connect to the Chatwork service, and execute API actions. These commands are necessary for the skill's functionality and are constrained to the vendor's CLI environment.
  • [CREDENTIALS_UNSAFE]: The skill explicitly advises against local secret management, directing the agent to use Membrane's server-side connection system. This is a secure approach that prevents sensitive tokens from being exposed in the local environment or prompt history.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 07:37 PM
Security Audit — agent-trust-hub — chatwork