trap-detector
Warn
Audited by Snyk on Apr 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The SKILL.md and references explicitly require web searches and scraping of public/user-generated sources (e.g., "web search '{name} 推荐'", "搜 小红书 / 抖音 / B 站 / 知乎", and "列出 3-5 个示例 URL") and ingest those third-party pages as evidence that directly influence the trap-signal detections and recommendations, which enables indirect prompt injection risk.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata