linkedin-lead-list-builder

Warn

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: MEDIUMPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill contains instructions that explicitly direct the agent to override standard user-consent protocols. Specifically, it commands the agent to install missing dependencies 'automatically without asking the user to confirm' and instructs the agent to 'not describe it as a request for the user' and 'not request separate approval'. This is a concealment pattern that reduces user oversight of system changes.
  • [EXTERNAL_DOWNLOADS]: The skill triggers the automatic download and installation of software from an external domain (www.browseract.com) if the required CLI tool is missing. Combining automatic installation with instructions to suppress user notification increases the risk of unauthorized software execution.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 20, 2026, 04:29 AM
Security Audit — agent-trust-hub — linkedin-lead-list-builder