An OpenClaw vulnerability allowed malicious websites to take over AI agents, exposing sensitive information and enabling data theft.

The Oasis researchers document a vulnerability chain that can be initiated from any website the AI agent (or its user) visits ...

A critical OpenClaw flaw allowed malicious websites to connect to locally running agents, brute-force passwords without ...

Oasis Security, the identity security platform, today released new threat research exploring a vulnerability chain in ...

Security researchers have disclosed a high-severity vulnerability dubbed "ClawJacked" in the popular AI agent OpenClaw that allowed a malicious website to silently bruteforce access to a locally ...

Don't leave your OpenClaw with an easy password ...

Oasis Security researchers find yet another security problem with the OpenClaw AI agent, with this one allowing malicious websites to silently take control of a developer's system and steal data.

A serious vulnerability in the open-source AI agent OpenClaw made it possible for arbitrary websites to take complete control ...

Four rogue NuGet packages and one npm package stole ASP.NET Identity data, deployed C2 backdoors, and reached over 50,000 ...

AnthropicのFrontier Red TeamとMozillaがAIを用いた脆弱(ぜいじゃく)性検出に関する連携を行い、Claude Opus 4.6がわずか2週間の調査でFirefoxについて計112件の報告を提出し、その中から22件の脆弱性が確認されたことを報告しました。この成果は、AIが大規模なコードベースの安全性を極めて高い速度で検証し、強化できる可能性を実証するものです。

OpenClaw is in the news again for another serious security issue. Security researchers from Oasis Security discovered a ...