chinese-domain-news
Warn
Audited by Snyk on Aug 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md 的运行时会对“每家公司”使用联网搜索工具去检索公司官网/百度百科等公开资料（外部网页或条目中的自由文本会被读取以支撑背景信息），因此存在被用户/第三方投毒内容间接喂给模型的风险。
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The README explicitly instructs the agent to load and follow remote skill instructions at runtime from https://raw.githubusercontent.com/leenbj/wangzhi-anli-skill/main/SKILL.md, which means fetched content would directly control agent prompts.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata