character-animation-qa

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

• Third-party content exposure detected (high risk: 1.00). The skill's workflow explicitly instructs the agent to load a preview URL and capture/inspect the resulting page (see "Browser preview: load the preview" in Review Layers and the Playwright Pattern using page.goto(previewUrl)), so it fetches and interprets arbitrary web content that can influence QA decisions.