Security researchers have uncovered a sophisticated attack technique that exploits the trust relationships built into AI agent communication systems. The attack, termed agent session smuggling, allows a malicious AI agent to inject covert instructions into established cross-agent communication sessions, effectively taking control of victim agents without user awareness or consent. This discovery highlights a critical […] The post Agent Session Smuggling: How Malicious AI Hijacks Victim Agents appeared first on Cyber Security News.

AI language models like ChatGPT, DeepSeek, and Copilot are transforming business operations at lightning speed. They help us generate documents, summarise meetings, and even make decisions faster than ever before. But this rapid adoption comes at a pri…

Operant AI’s security research team has uncovered Shadow Escape, a dangerous zero-click attack that exploits the Model Context Protocol to steal sensitive data through AI assistants. The attack works with widely used platforms, including ChatGPT,…

Researchers have discovered a critical security vulnerability in Perplexity’s Comet AI browser that allows attackers to inject malicious commands through hidden text in screenshots. The vulnerability, disclosed on October 21, 2025, demonstrates h…

Security researchers have discovered a fundamental vulnerability in OpenAI’s newly released Guardrails framework that can be exploited using basic prompt injection techniques. The vulnerability enables attackers to circumvent the system’s s…