AI cybersecurity is a cat and mouse gamejust now Google Research Releases ToolGrad: Answer-First Framework Hits 99.8% Pass Rate for Tool-Use Data Generation37m ago China's star AI labs routed user requests to Claude at least 35 million times in the summer: Anthropic50m ago Anthropic and OpenAI employees speak out about humanity’s extinction as debate reaches fever pitch53m ago Force launches chatbot for non-emergency calls59m ago Tesla unveils driverless Cybercab in Japan for 1st time1h ago How Maersk Is Using AI To Survive The New Era Of Tariff Chaos1h ago Russia to require content made by, with AI to be labeled as such — GFCN president2h ago Flipkart’s Super.money Bets on AI Agents to Outdo Bigger Rivals3h ago Datasette 1.0a39 and 0.65.4 security releases3h ago Anthropic caught scientists using Claude to further biological weapon research4h ago Oracle says AI will save it from the SaaSpocalypse, not bring it on4h ago Congress Is Suddenly Waking Up to the AI Doomsday Threat5h ago Don’t ask ChatGPT 'What should I do?' — this simple prompt helps you make better decisions yourself5h ago

AI cybersecurity is a cat and mouse gamejust now Google Research Releases ToolGrad: Answer-First Framework Hits 99.8% Pass Rate for Tool-Use Data Generation37m ago China's star AI labs routed user requests to Claude at least 35 million times in the summer: Anthropic50m ago Anthropic and OpenAI employees speak out about humanity’s extinction as debate reaches fever pitch53m ago Force launches chatbot for non-emergency calls59m ago Tesla unveils driverless Cybercab in Japan for 1st time1h ago How Maersk Is Using AI To Survive The New Era Of Tariff Chaos1h ago Russia to require content made by, with AI to be labeled as such — GFCN president2h ago Flipkart’s Super.money Bets on AI Agents to Outdo Bigger Rivals3h ago Datasette 1.0a39 and 0.65.4 security releases3h ago Anthropic caught scientists using Claude to further biological weapon research4h ago Oracle says AI will save it from the SaaSpocalypse, not bring it on4h ago Congress Is Suddenly Waking Up to the AI Doomsday Threat5h ago Don’t ask ChatGPT 'What should I do?' — this simple prompt helps you make better decisions yourself5h ago

Cybersecurity Agents7 min reading time

AI "Mind Viruses" Can Spread Between Agents Through Persistent Prompt Files

The Hacker NewsPublished 24 days ago

Researchers at Anthropic and EPFL showed that AI agents can transmit self-propagating 'mind virus' payloads via persistent system prompt files, but a simple warning greatly limits spread. Tests involved simulated coding agents and OpenClaw-based pairs, with no evidence of real-world spread.

#ai-security #anthropic #autonomous-agents #claude-haiku-4-5 #epfl #openclaw #prompt-injection

More in Cybersecurity

Cybersecurity10 min read

Anthropic Details Disrupted Claude Misuse Across Seven Harm Areas

Covered by 4 sources13h ago

Cybersecurity4 min read

Sam Altman met with top power utilities about securing the electrical grid. He offered one possible solution: OpenAI's cyber services.

Covered by 2 sources10h ago

Cybersecurity6 min read

Anthropic reveals rogue AI agents hate CAPTCHAs, just like you

TechCrunch13h ago