image-generation

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md "With Reference Image" workflow shows the agent accepting an arbitrary image_url (e.g., https://example.com/reference-style.jpg) which the service will fetch and use to influence image generation, meaning untrusted third‑party content can be ingested and affect the agent's outputs.