A high-severity OpenClaw flaw allows one-click remote code execution via token theft and WebSocket hijacking; patched in ...

Researchers disclose rapid exploit chain that let attackers run code via a single malicious web page Security issues continue ...

OpenClaw patched a critical vulnerability that could be exploited to hijack the increasingly popular AI assistant.

OpenClaw has exposed users to critical security vulnerabilities, including CVE-2026-25253 enabling one-click remote code ...

API keys and credentials. Agents operate inside authorized permissions where firewalls can't see. Traditional security models ...

The AI bot OpenClaw, also known as Moltbot, can do a lot on user computers. A code smuggling vulnerability within it is ...

前两天写了篇《初识 Moltbot》，总觉得差点意思。这次又翻了些源码和实现细节，想把 Moltbot 再讲透一点。看似驳杂的超级缝合怪，实则蕴含诸多巧妙且先进的设计理念。简单背后的不简单，注定结果非凡！让我们先来看张截图（GitHub ...