bux-claude-agent

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow sets up a Telegram bot bridge that ingests messages from any Telegram user into a Claude agent running in browser automation mode, exposing the agent to untrusted external input.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the user to pipe a remote install script directly from GitHub (https://raw.githubusercontent.com/browser-use/bux/main/install.sh) into bash with superuser privileges, constituting an unverified third-party runtime dependency.