Skills
skills/membranedev/application-skills/knock/Gen Agent Trust Hub

knock

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected.
  • [EXTERNAL_DOWNLOADS]: The skill installs and uses the official @membranehq/cli package from the public npm registry, which is a trusted vendor resource for this skill.
  • [COMMAND_EXECUTION]: Shell commands are used to interact with the Membrane platform (e.g., membrane login, membrane connect, membrane action run). These are standard operations for the tool's intended purpose.
  • [CREDENTIALS_UNSAFE]: The skill implements strong security practices by explicitly instructing the agent to never ask users for API keys or tokens, instead utilizing server-side credential management via the membrane connect workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 10:27 PM