python-team
Warn
Audited by Snyk on Feb 19, 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). Yes — the skill's Stage 0 "自主学习与知识整合" and the "核心要求(强制)" explicitly require performing web searches (执行网络搜索(3-6轮) / 必须执行网络搜索,不得跳过) and instruct the agent to read and integrate open web search results into background.md which are untrusted third‑party pages and will directly influence architecture, technology selection, and subsequent actions.
Audit Metadata