using-agent-browser

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

• Third-party content exposure detected (low risk: 0.10). The agent-browser skill instructs the agent to navigate to arbitrary URLs (such as user-supplied web pages or external applications) and interact with them, exposing the LLM to untrusted web content via browser automation.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill instructs the agent to run sudo apt-get install to install packages, which involves privilege escalation and modifying system state using sudo.