"I did a proper backdoor." The post It’s Laughably Easy to Poison Open-Weight AI Models, Researcher Finds appeared first on ...

Hugging Face experienced a sophisticated AI agent-driven cyberattack. US-made AI models blocked attempts to neutralize the ...

A flaw in Hugging Face Transformers could allow malicious AI models to execute code, exposing credentials and highlighting AI supply chain risks. Organizations using vulnerable versions of the Hugging ...

Hugging Face says an autonomous AI agent breached production through a malicious dataset, accessing internal data and service ...

A cybersecurity researcher poisoned an open weight AI model for under $100 in about an hour, exposing how easily these increasingly popular systems can be secretly compromised without detection.

Researchers warn AI agents could be tricked into downloading malicious code by exploiting hallucinations that cause chatbots ...

Straiker, The Agentic Security Company, today released the inaugural threat report from its STAR Labs team. To understand the real-world risk AI agents pose to enterprises, researchers ran thousands ...

A newly-disclosed exploit in Claude Code’s ‘auto-mode’ leaves developers facing remote code execution (RCE) vulnerabilities ...

Unsafe defaults in MCP configs open servers to possible remote code execution, as evidenced by several commercial services and open-source projects. AI agent building tools enable users to configure ...