Mozilla 0DIN’s Claude Code demo shows how clean GitHub repos can expose AI coding agents to prompt injection, reverse shells, and credential risk.

US LNG exports to Europe decline as Asia prices surge For the first time in nearly two years, less than half of U.S. LNG ‌exports last month went to Europe as stronger prices in Asia and record ...

安全扫描器看到的可能是命令注入、路径穿越、不安全反序列化、敏感信息泄露等常见漏洞；但在 Agent Skill 场景里，这些“普通漏洞”可能会被 Agent 主动触发，并且带着文件权限、项目上下文、环境变量、Git 凭据、MCP 配置和 Agent 记忆一起进入执行链。