marketing-setup

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

• Third-party content exposure detected (high risk: 0.70). Step 0 performs runtime filesystem scanning of outsider-authored files (e.g., **/portfolio.json, **/tips-project.json, and optional output/communicate/customer-narrative/ files) and then “present[s] discovered sources to user”/stores discovered narrative paths for later use, which can lead the agent’s LLM context to include free-text from those outsider documents.