A security vulnerability in ChatGPT executed with a single malicious prompt could be exploited to covertly exfiltrate ...

Researchers uncovered a ChatGPT vulnerability enabling hidden data leaks, highlighting security gaps and the need for ...

Antigravity IDE allows agents to execute commands automatically under default settings Prompt injection attacks can trigger unwanted code execution within the IDE Data exfiltration occurs through ...

The Check Point security bods explain that, while OpenAI prevents ChatGPT from communicating with the internet without ...

AI copilots are incredibly intelligent and useful — but they can also be naive, gullible, and even dumb at times. A new one-click attack flow discovered by Varonis Threat Labs researchers underscores ...

BeyondTrust shows how AWS Bedrock AgentCore’s ‘isolated’ environment can be tricked into data exfiltration and command execution via DNS. AWS’ promise of “complete isolation” for agentic AI workflows ...

Command injection in Codex and a hidden outbound channel in ChatGPT exposed risks of credential theft and covert data ...

The stakes have never been higher for accounting firms. As custodians of sensitive financial data, tax returns, payroll records and audit reports, these businesses are prime targets for a rapidly ...

Unlike traditional infostealers that run once and exit, Venom Stealer remains active and continuously monitors Chrome's login ...

Delivers the visibility and control required to secure autonomous AI agents across critical workflows. One in eight AI breaches are linked to agentic systems, according to HiddenLayer's 2026 AI Threat ...