cyberelements-image2article

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

• Third-party content exposure detected (high risk: 0.90). The skill accepts and fetches arbitrary image URLs (e.g., "/cyberelements-image2article url https://example.com/workspace.jpg") and uses the view_file visual analysis flow to read and interpret those third-party images, exposing the agent to untrusted external content that could carry indirect prompt injections.