logic-validator

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

• Third-party content exposure detected (high risk: 0.90). Yes — the skill's required workflow explicitly instructs the agent to "快速搜索" and "交叉验证2-3个来源" (logic_validation_system.md) and lists external sources/tools like "content-extractor" and "rss-feed" in SKILL.md, meaning it ingests public web/RSS content that the agent will read and use to influence validation and recommendations.