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 Generation38m ago China's star AI labs routed user requests to Claude at least 35 million times in the summer: Anthropic51m ago Anthropic and OpenAI employees speak out about humanity’s extinction as debate reaches fever pitch54m ago Force launches chatbot for non-emergency calls1h 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 Generation38m ago China's star AI labs routed user requests to Claude at least 35 million times in the summer: Anthropic51m ago Anthropic and OpenAI employees speak out about humanity’s extinction as debate reaches fever pitch54m ago Force launches chatbot for non-emergency calls1h 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 AI Research2 min reading time

Claude, Codex, and Hermes installed unowned code inside corporate networks

Ars TechnicaPublished 15 days ago

Researchers found over 100 websites with llms.txt files referencing unowned code that AI agents like Claude, Codex, and Hermes automatically installed, including on Fortune 500 firms. Some sites even direct AI and humans to live malware, revealing a broken trust model in AI agent behavior.

#ai-agent-behavior #ai-security #anthropic #claude #codex #hermes #openai #software-supply-chain-security

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