Content-Judge
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly accepts "输入任意内容" and lists examples like "高赞公众号文章" and "小红书内容", so the agent is expected to ingest and analyze user-provided, public/social user-generated content (untrusted third‑party content) as part of its workflow, enabling indirect prompt injection.
Audit Metadata