lemlist
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
@membranehq/clipackage from the public NPM registry. This tool is the primary interface for the skill's functionality and is a resource provided by the skill's authoring organization. - [COMMAND_EXECUTION]: The skill relies on executing the
membranecommand-line utility to manage Lemlist connections, search for available actions, and perform API requests. These commands are part of the intended integration workflow. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface where user-supplied natural language intents and structured JSON parameters are passed into CLI commands to interact with the Lemlist API.
- Ingestion points: User-provided query strings for action discovery and input objects for action execution.
- Boundary markers: None explicitly defined in the prompt templates.
- Capability inventory: The skill can perform network operations and API requests through the Membrane proxy service.
- Sanitization: Relies on the underlying CLI and backend service to validate inputs before transmission to the Lemlist API.
Audit Metadata