last30days-cn
Warn
Audited by Snyk on Jul 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). High chance: the runtime pipeline fetches outsider-authored text from public platforms (e.g., Weibo/Xiaohongshu/Bilibili/Zhihu/Douyin/WeChat/Baidu/Toutiao and Bing site-search fallbacks) via the skill scripts and then emits that evidence (including a
contextsnippet) into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata