fund-research

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 perform "全网深度搜索" and "X/Twitter 实时动态监控" and to call deep-research/x-research-skill to ingest web and social-media content for gap analysis, which means the agent will fetch and interpret untrusted public third-party content that can influence its decisions.