smoke-test

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

• Third-party content exposure detected (high risk: 0.90). The skill's run loop and execution guide explicitly direct the agent to navigate to and validate a target URL supplied by the smoke file or the user (see "Resolve target URL" in references/execution.md and the SKILL.md run steps) using the browse tool, so it will load and interpret arbitrary external webpages whose content can influence authentication, case decisions, and subsequent tool actions.