leadsquared
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@membranehq/cliNode.js package. This is an official tool provided by the vendor (Membrane) to facilitate platform integrations. - [COMMAND_EXECUTION]: The skill utilizes several shell commands via the Membrane CLI to perform tasks such as logging in, connecting to LeadSquared, and executing CRM actions. These are documented functionalities of the platform.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it retrieves and processes data from LeadSquared (leads, activities, tasks). If external actors can influence this data, it could potentially contain instructions intended for the agent. However, this is a common characteristic of CRM integrations and the risk is considered low within this context.
- [REMOTE_CODE_EXECUTION]: The
membrane action createcommand allows the dynamic generation of new actions based on natural language descriptions. While this involves generating executable logic at runtime, it is a core feature of the Membrane platform's automated integration capabilities and is managed server-side by the vendor.
Audit Metadata