dino-note

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

• Third-party content exposure detected (medium risk: 0.65). Outsider-authored free text can enter the LLM context when the workflow performs note reads (e.g., dino note detail / dino note preview / dino note get --context-only) because those commands return markdown/content authored by other parties, which the agent then uses in its reasoning context.