Skills
skills/membranedev/application-skills/21risk/Gen Agent Trust Hub

21risk

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package via NPM. This is the official command-line interface provided by the vendor (Membrane) to manage integrations.
  • [COMMAND_EXECUTION]: The skill utilizes several shell commands via the membrane CLI to perform login, connect to the 21RISK service, search for available actions, and execute workflows. These commands are essential for the skill's documented functionality.
  • [SAFE]: The skill follows security best practices by advising users to let the Membrane platform handle authentication and credentials server-side, rather than hardcoding secrets or requesting them directly. No malicious patterns such as prompt injection or obfuscation were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 02:30 PM
Security Audit — agent-trust-hub — 21risk