larry-playbook

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow includes “Hourly research — Find trending hooks, viral topics” which typically fetches public web/social content and then feeds that scraped outsider text into the agent’s LLM context for hook/caption generation (public web content fetched at runtime → LLM-readable prose).