four-knowns

Warn

Audited by Snyk on Mar 6, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md explicitly requires locating and citing external sources (e.g., "主要的paper", "近 6 个月重大动态", market data and the "数据有出处" requirement), which clearly entails fetching/ingesting public third-party papers, news, and websites that could contain untrusted instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 6, 2026, 03:28 AM