mega-campaign-generator

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow explicitly ingests “source docs or threads” and “chat or collaboration tools threads” via Zapier MCP (“read approved docs… and collaboration threads”), which can include outsider-authored free-form text (e.g., comments/messages/issues) that the agent then uses to generate LLM context.