theory-analysis-purchase-motivation

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

• Third-party content exposure detected (high risk: 0.90). The skill's Input Contract requires ingesting evidence_items.content and the Theory Foundation and Workflow (references/00-theory-foundation.md and SKILL.md) explicitly list social posts, support tickets, and other user-generated/public sources as allowable evidence that the agent must read and code, so untrusted third-party content can directly influence its analysis and outputs.