aivie

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the official npm registry. This is a standard global installation of the vendor's command-line tool.
  • [COMMAND_EXECUTION]: The skill utilizes several membrane CLI commands (e.g., membrane login, membrane action list, membrane action run) to interact with the platform. These are standard operations for the tool's intended purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill contains surfaces where untrusted data (user-provided intents or action descriptions) are interpolated into shell command arguments.
  • Ingestion points: User-provided query strings in the SKILL.md instructions for membrane action list --intent "QUERY" and membrane action create "DESCRIPTION".
  • Boundary markers: None; parameters are passed as plain string arguments within shell commands.
  • Capability inventory: The skill executes shell commands via the CLI to list, create, and run actions.
  • Sanitization: No explicit sanitization or escaping is mentioned in the instructions for the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 11:33 AM
Security Audit — agent-trust-hub — aivie