ai-avatar-generation

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests untrusted third-party content via user-supplied image URLs in SKILL.md examples ("image_urls": ["https://example.com/my-photo.jpg"]) and also documents performing web searches and returning web_search_citations in references/SSE-EVENTS.md, both of which the agent is expected to read/interpret and can materially affect generation/next actions.