Researchers discovered a security flaw in Google's Gemini AI chatbot that could put the 2 billion Gmail users in danger of being victims of an indirect prompt injection attack, which could lead to ...

A critical LangChain AI vulnerability exposes millions of apps to theft and code injection, prompting urgent patching and ...

While the shortest distance between two points is a straight line, a straight-line attack on a large language model isn't always the most efficient — and least noisy — way to get the LLM to do bad ...

At 39C3, Johann Rehberger showed how easily AI coding assistants can be hijacked. Many vulnerabilities have been fixed, but ...

A critical LangChain Core vulnerability (CVE-2025-68664, CVSS 9.3) allows secret theft and prompt injection through unsafe ...

The vulnerability, tracked as CVE-2025-68664 and dubbed “LangGrinch,” has a Common Vulnerability Scoring System score of 9.3.

CISA adds an actively exploited Digiever DS-2105 Pro NVR vulnerability to KEV, warning of botnet attacks and urging ...

OpenAI has deployed a new automated security testing system for ChatGPT Atlas, but has also conceded that prompt injection ...

Motherboards from several major vendors are affected by a vulnerability that can allow a threat actor to conduct early-boot attacks.

HPE has released patches for a critical-severity OneView vulnerability that could lead to unauthenticated remote code execution.

Hewlett Packard Enterprise (HPE) has patched a maximum-severity vulnerability in its HPE OneView software that enables attackers to execute arbitrary code remotely.

Seatbelts don’t make you invincible. You can drive the safest car on the road and still end up in an accident if you can't see your surroundings. The same principle applies to citizen developer ...