openai-api

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

• Third-party content exposure detected (high risk: 0.70). The skill's Vision examples (e.g., "Image via URL" in the Vision (GPT-4o) section and related templates) explicitly accept arbitrary external image URLs (image_url) that the model will fetch and interpret at runtime, exposing it to untrusted third‑party content that could carry indirect prompt injections.