ui-cloner-iterator

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md requires the agent to "scan the current implementation" which can be a user-provided URL and explicitly mandates "Use Claude with chrome for visual checking MANDATORY," meaning the agent will fetch and interpret arbitrary public web pages/screenshots as part of its iterative corrective workflow, exposing it to untrusted third-party content.