ai-viral-team-script-writing

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

• Third-party content exposure detected (high risk: 0.70). The skill's required workflow ("处理方式" in SKILL.md) explicitly instructs that if the user chooses "自动适配", the agent will "在网络上搜索对应图片，让用户确认", meaning it fetches/searches public web images (untrusted third-party content) and uses them to adapt character assets and drive subsequent generation decisions.