lusha

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill specifies the installation of @membranehq/cli via npm. This is a trusted resource from the official vendor scope.
  • [COMMAND_EXECUTION]: Functionality is implemented through standard membrane CLI commands for connection and action management. These are restricted to the intended purpose of the Lusha integration.
  • [PROMPT_INJECTION]: The skill retrieves contact and company information from the Lusha API.
  • Ingestion points: Data enters the context via membrane action run output (SKILL.md).
  • Boundary markers: None present.
  • Capability inventory: The skill allows for action execution and connection management within the Membrane platform; it does not have access to sensitive local files or system configuration.
  • Sanitization: Not specified in the instructions, however, the limited capabilities of the skill reduce the impact of potential indirect injections.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 09:38 PM
Security Audit — agent-trust-hub — lusha