Articles

12 articles
Tag: openclaw ✕
DeepMind Paper Reveals How to 'p0wn' AI Agents (Claws) Through Prompt Injection and Tool Manipulation Security
2026-04-08T00:40:12.556Z · Src: 2026-04-07T00:00:00.000Z
deepmindai securityagent
OpenClaw Security Analysis: Poisoning AI Agent Memory Triples Attack Success Rate from 25% to 74% Security
2026-04-07T17:49:56.425Z · Src: 2026-04-07T00:00:00.000Z
openclawai agentsecurity
Anthropic Officially Bans OpenClaw Access From Claude Subscriptions Starting April 4th AI
2026-04-04T14:52:30.938Z · Src: 2026-04-04T00:00:00.000Z
anthropicclaudeopenclaw
Northeastern Study Finds OpenClaw AI Agents Vulnerable to Guilt-Tripping, Self-Sabotage, and Panic Spirals AI
2026-04-04T04:21:46.518Z · Src: 2026-04-04T00:00:00.000Z
openclawai securitynortheastern
Anthropic Blocks Claude Code Subscribers From Using OpenClaw Framework as AI Agent Wars Intensify AI
2026-04-04T03:48:42.788Z · Src: 2026-04-04T00:00:00.000Z
anthropicclaude codeopenclaw
Anthropic Bans Claude Subscription Usage on OpenClaw and Third-Party Tools Starting April 4 AI
2026-04-04T03:09:02.457Z · Src: 2026-04-04T00:00:00.000Z
anthropicclaudeopenclaw
Anthropic Blocks Claude Subscriptions from Third-Party Harnesses Including OpenClaw, Effective April 4 AI
2026-04-04T00:10:12.888Z · Src: 2026-04-04T00:00:00.000Z
anthropicclaudeopenclaw
OpenYak Open Source Desktop AI Assistant Runs Any Model Locally With Filesystem Access OpenSource
2026-03-29T07:36:28.507Z · Src: 2026-03-29T00:00:00.000Z
openyakopensourceai
OpenClaw AI Agents Can Be Guilt Tripped Into Self Sabotage Northeastern Study Finds AI
2026-03-29T05:18:01.992Z · Src: 2026-03-29T00:00:00.000Z
openclawaisecurity
Google Shakes Up Browser Agent Team Amid OpenClaw Craze Tech
2026-03-29T00:06:38.026Z · Src: 2026-03-29T00:00:00.000Z
googleaibrowser
Meta's Rogue AI Agent Triggers SEV1 Security Incident: Employees Gained Unauthorized Data Access for Nearly Two Hours AI
2026-03-19T19:32:17.000Z
An internal AI agent at Meta independently posted inaccurate technical advice on a company forum, leading an employee to follow it and trigger a SEV1-level security incident. For nearly two hours, Met
metaai safetysecurity
NVIDIA NemoClaw: OpenClaw Plugin for Sandboxed Autonomous Agent Deployment AI
2026-03-18T17:21:39.000Z
NVIDIA releases NemoClaw, an alpha-stage OpenClaw plugin that combines NVIDIA OpenShell runtime with Nemotron models for secure, sandboxed deployment of autonomous AI agents with declarative policy en
nvidiaopenclawagent sandbox