2chat

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package via NPM. This is a verified resource from the author (membranedev) used to provide the skill's core functionality.
  • [COMMAND_EXECUTION]: The skill uses membrane CLI commands to manage authentication, discover actions, and execute integrations. These are authorized and expected commands for the skill's purpose.
  • [CREDENTIALS_UNSAFE]: The skill follows secure credential management patterns by using the Membrane platform's authentication flow instead of requiring or storing API keys directly.
  • [PROMPT_INJECTION]: The skill ingests data from 2Chat via action outputs, which is a potential surface for indirect prompt injection. However, this is managed as part of the normal operation of a data-fetching integration.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 01:41 PM