content-to-pipeline

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Reverse Engineering Process" and "Audience Research Stack" explicitly instruct the agent to identify and export top-performing posts from public social accounts (via manual scroll, Viral Findr, Taplio, SparkToro, X search, etc.), which requires ingesting untrusted, user-generated third-party content that can materially influence templates and next actions.