corrinehu-kimi-searchzhihu

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to open and search Zhihu (e.g., "open https://www.zhihu.com/search?q=关键词" and related login/search workflows), a public, user-generated site whose content the agent will read and act on, so untrusted third-party content could indirectly inject instructions.