botconversa

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

• Third-party content exposure detected (high risk: 0.80). The skill's core workflow uses the Membrane CLI to run actions against the third‑party BotConversa platform (e.g., list-subscribers, list-flows, get-campaign, send-message-to-subscriber) which ingests and returns user-generated conversation/subscriber content that the agent is expected to read and could materially influence subsequent actions.