browse

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill tells the agent to ask the user for credentials and then embed those values verbatim in browser_type commands (e.g., text: ""), which requires the LLM to handle/output secrets directly.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to use browser_navigate({ url: "" }) and then read page content via browser_snapshot, browser_console_messages, and browser_evaluate to decide clicks/fills/waits, meaning it loads arbitrary public web pages whose untrusted content can influence subsequent actions.