character-design-sheet

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

• Third-party content exposure detected (low risk: 0.10). The workflow ingests only the user-supplied --input JSON prompt text into belt app run falai/flux-dev-lora (and similar), which is free text but is not a runtime consumer of outsider-authored third-party content like emails/inboxes/feeds/issues.