browser-use

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes commands and examples that embed secrets verbatim (e.g., browser-use input 6 "password" and browser-use cookies set <name> <value>), so an agent would be required to include user credentials/cookie values directly in generated commands.

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly opens and interacts with arbitrary web pages (SKILL.md core workflow and commands like "browser-use open ", "browser-use state", "browser-use get html/get text" and the cdp-python reference), so the agent ingests untrusted public web content which can directly influence subsequent clicks, inputs, JavaScript evals, and decision-making, enabling indirect prompt injection.