book-idea-validator

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly requires the agent to perform a "Landscape scan" where "Claude searches each claim area" and to consider "Objections Reader Will Google" (i.e., web/search results and public sources) to produce the Validation Report, meaning it ingests open/public third-party content that directly influences go/revise/kill decisions and could enable indirect prompt injection.