image-playground

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

• Third-party content exposure detected (high risk: 0.70). The skill's references/playwright-download.md explicitly instructs a browser-based workflow to visit and scrape https://chatgpt.com/images (a public, user-generated image history) to detect and download the newest image, which the agent is expected to read/interpret and act on—exposing it to untrusted third-party content that could influence subsequent actions.