memoriesweave

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

• Third-party content exposure detected (high risk: 0.70). The skill's workflows explicitly fetch and consume user-generated content — e.g., GET /workspaces/{wsId}/conversations (WhatsApp conversation chunks) and GET /memories/{id}/html (self-contained memory HTML and public share URLs) — which the agent is expected to read/interpret and which can materially influence AI design/content jobs and follow-up actions.