cover-image

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly saves and analyzes arbitrary user-provided/pasted content and files from the conversation ("If user pastes content: save to source.md", "Multiple sources supported: text, images, files from conversation"), meaning untrusted third‑party content is ingested and interpreted as part of the workflow.