openclaw-executive-assistant-webinars

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

• Third-party content exposure detected (high risk: 0.85). Outsider free text can enter the LLM context via the runtime ingestion of user-provided files in incoming/, inbox/, and especially exported .eml files in 03-offline-communications-triage/eml/, whose contents are authored by other people (email senders) and are then processed by the prompt.