OpenAI introduced GPT-Red, an automated AI system designed to find vulnerabilities in GPT models before release. The company said GPT-Red was used to train GPT-5.6, reducing failures on one of its ...

AWS fixed a Kiro prompt injection chain that rewrote mcp.json and launched attacker-controlled code with developer privileges ...

Open-source Android AI agents can turn hidden screen text into host commands, and all five tested frameworks failed at least ...

When combined with another exploit, the "PromptFiction" vulnerability, which has been fixed, could have enabled an end-to-end ...

In June 2025, Microsoft patched CVE-2025-32711, better known as EchoLeak: a zero-click vulnerability in Microsoft 365 Copilot ...

Researchers have demonstrated GhostWriter, a new attack that secretly injects false memories into AI agents, influencing ...

Context bomb cybersecurity research from Tracebit shows that a single hidden text string inside an AWS cloud decoy stopped ...

(NYSE: BOX), the leading Intelligent Content Management (ICM) platform, today announced new security capabilities designed to give organizations greater control over AI agents working with enterprise ...

Red, an internal artificial intelligence system trained to attack the company’s own models, expose their vulnerabilities, and ...

Red, an internal artificial intelligence system it built to attack its own models and surface prompt injection ...

CLEVELAND, Ohio — Ohio regulators spurred four Washington County injection wells that receive fracking waste to stop ...

By turning prompt injections and LLM safety guardrails against malicious AI agents, a creative new cyber defense adds attack ...