ChatGPT and Codex flaws patched Feb 2026 exposed DNS exfiltration and GitHub tokens, raising enterprise AI security risks.

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

OpenAI talks up data security for its AI services, yet Check Point says that ChatGPT allowed data to leak through a DNS side ...

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

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

HYCU, Inc., a leader for modern data protection for on-prem, cloud, and SaaS and one of the fastest growing companies in the industry, today announced a major expansion of its R-Shield cyber ...

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 ...

A legitimate Google ad could lead to data exfiltration through a chain of Claude flaws.

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 ...

Autonomous artificial intelligence (AI) agents are rapidly entering real-world healthcare systems, but new research warns ...

One in eight AI breaches are linked to agentic systems, according to HiddenLayer's 2026 AI Threat Landscape Report. Each ...