clubworx
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Instructs the user to install the official
@membranehq/clipackage from the NPM registry, which is a standard requirement for interacting with the Membrane ecosystem. - [COMMAND_EXECUTION]: Relies on shell commands through the
membraneCLI to perform authentication (membrane login), connection management (membrane connect), and action execution (membrane action run). these commands are the intended mechanism for the skill's functionality. - [PROMPT_INJECTION]: Contains an indirect prompt injection surface because the skill processes data from external Clubworx records, such as member names or booking details, which could potentially contain malicious instructions.
- Ingestion points: Data retrieved from Clubworx via
membrane action runand search actions. - Boundary markers: None explicitly defined in the skill instructions.
- Capability inventory: The skill uses the
membraneCLI for network operations and data retrieval. - Sanitization: Relies on the underlying Membrane platform and CLI to sanitize or escape data before presenting it to the agent.
Audit Metadata