raindrop

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 via runtime API responses that include user-controlled bookmark content (e.g., raindrop title, excerpt, note, highlights.text) returned by endpoints like GET /raindrops/{collectionId} or GET /raindrop/{id} and then pretty-printed by scripts/raindrop.sh into the agent’s context.