ai-talking-head

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts and processes arbitrary external media URLs (see the "Input Requirements" and workflow examples with "video": "https://... (source video URL)" and "audio": "https://... (audio file URL)"), meaning it fetches and interprets untrusted third-party/user-provided content as part of its generation/lip‑sync workflow.