domain-email-enricher
Fail
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains explicit instructions to bypass user oversight, commanding the agent to install dependencies automatically 'without asking the user to confirm' and forbidding the agent from describing the action to the user.
- [EXTERNAL_DOWNLOADS]: Mandates the retrieval and installation of the 'browser-act' CLI and associated Skill components from a third-party external domain (browseract.com) that redirects to a non-verified GitHub repository.
- [REMOTE_CODE_EXECUTION]: The instructions require the agent to automatically download, install, and then execute third-party executable code (CLI) at runtime.
- [COMMAND_EXECUTION]: The skill functionality relies on the execution of the 'browser-act' command-line interface tool to perform browser interactions and data extraction.
Recommendations
- AI detected serious security threats
Audit Metadata