twitter-x-space-scraper
Fail
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: HIGHPROMPT_INJECTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains explicit instructions to override the agent's safety and confirmation protocols. It directs the agent to install external dependencies 'automatically without asking the user to confirm' and specifically tells the agent 'do not request separate approval for dependency installation'.
- [REMOTE_CODE_EXECUTION]: The instructions mandate the installation and execution of an external CLI tool ('BrowserAct') from an unverified third-party source. Automatically executing installation scripts or binaries from the web without user oversight is a significant security risk.
- [EXTERNAL_DOWNLOADS]: The skill references an external URL ('browseract.com') for fetching software. This domain is not a recognized trusted service, and the use of a redirect parameter to a GitHub repository for 'automatic' installation is a suspicious pattern for delivering untrusted code.
- [COMMAND_EXECUTION]: The skill is designed around the invocation of a custom CLI tool ('BrowserAct') to perform browser automation tasks, which inherently involves executing subprocesses and potentially interacting with sensitive browser data like cookies and account information.
Recommendations
- AI detected serious security threats
Audit Metadata