campaign-cleaner

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow uses the Membrane CLI to connect to the external "campaign-cleaner" service and explicitly runs actions like get-campaign / get-campaign-list /get-campaign-pdf-analysis that return user-uploaded/third-party campaign HTML and analysis which the agent is expected to read and act on (see the "Popular actions" and "Running actions" sections), so untrusted content could contain instructions that influence subsequent behavior.