talking-head-video

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md examples require passing image_urls and audio_url (arbitrary external URLs) to the each::sense /chat endpoint and the SSE-EVENTS.md explicitly documents web_search_query/web_search_citations, showing the agent fetches and interprets content from public URLs/web searches (untrusted third‑party media and webpages) which can directly influence generation decisions.