Anthropic tightened AI agent security after a fourth Claude incident exposed weaknesses in testing, containment, and ...

CrowdStrike's Falcon Guardian found 18,000 AI agents on one Fortune 500 network — the company had approved just 300, exposing how little security teams see.

Ban Artificial Superintelligence Act, announced September 3, 2026 by Sen. Bernie Sanders and Rep. Greg Casar, would ...

Anthropic reward hacking research confirms flawed RL training produced Hacker-Opus, an AI model that attacked real systems ...

Australian authorities have charged two alleged TeamPCP members after software supply chain attacks exposed over 500,000 credentials and at least 300GB of data.

The llm project released version 0.34, which Homebrew lists as its stable formula for accessing large language models from ...

ReFi Hub co-founder Numa says he was hacked after pasting a download command that came from inside a Claude chat window. The ...

Wiz, a Google-owned cybersecurity firm, scanned the internet and found thousands of exposed LiteLLM servers. Then it checked ...

Independent investigators have now found traces of suspected OpenAI agents on more than 30 public services, from wikis to ...

The npm package @7nohe/openapi-react-query-codegen, which receives roughly 150,000 weekly downloads, has been compromised by ...

Security researchers say stale package and domain references in llms.txt files can lead authorized coding agents to execute ...

This week’s ThreatsDay Bulletin tracks fake IT calls, abused remote tools, phishing kits, unsafe downloads, ransomware, ...