market-landing

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly requires a user-provided landing page URL and instructs the agent to analyze page content (e.g., "User provides a landing page URL" and "If you have access to the page via browser tools, take screenshots and reference specific elements" in SKILL.md), which means it fetches and interprets arbitrary public web pages as part of its workflow, exposing the agent to untrusted third-party content.