proxy-tool-bootstrap

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). This document provides explicit, step-by-step instructions for evasion (proxy/Tor rotation), automated credential attacks, tooling to perform scans/exploits without safeguards, and OOB callback infrastructure — all indicators of deliberate offensive/malicious intent.

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

• Third-party content exposure detected (low risk: 0.10). 该运行流程主要通过curl从外部探测/代理池接口获取可用代理（如 ip-api.com、proxyscrape.com），并未对“被第三方作者提交的自由文本”进行LLM读取/注入式消费；它更像是工具化网络探测而非让代理把用户文本喂给LLM。