wudao-hero

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly reads and ingests untrusted third-party/user-generated content—e.g., trading screenshots, 微信/QQ group exports (tools/wechat_parser.py), 雪球/forum posts (tools/xueqiu_parser.py) and general social media screenshots (tools/social_parser.py)—and then incorporates extracted insights into the user's Trading DNA and profile files (trading-dna.md, experience-log.md, cross-skill-log.md), which can materially change the agent's subsequent recommendations and behavior.