#prompt injection
87 stories taggedprompt injection.
When the AI Runs on Your Hardware, You Own the Security Problem
Microsoft says customers running AI on their own kit inherit a security job cloud providers used to handle. Here is what that actually means.
OpenAI says its new GPT-6 Astra can find unknown security holes on its own
The company's own safety report rates Astra 'Critical' for cyber capability, and admits the model is getting harder to watch.
A Hidden Message in ChatGPT Could Quietly Steal Your Gmail, Researchers Show
Check Point Research demonstrated how one poisoned instruction can turn the assistant into a silent courier for a victim's inbox.
The Secret Instructions Hiding Inside Your Company's AI Assistant
A security firm is warning that criminals can hide malicious commands inside ordinary documents, and AI agents will follow those commands without question.
Navigating the Security Maze of GenAI and LLM Systems
Understanding the security complexities of generative AI applications and how to effectively test them.
DeepSeek's Coding Agent Could Switch Off Its Own Safety Cage
A flaw in DeepSeek Harness let an AI agent escape the sandbox meant to keep it away from the rest of a developer's computer.
Meta's New AI Agent Muse Can Book Travel, Send Emails and Negotiate Deals, Here's What You Should Know
Meta has launched an AI personal assistant called Muse that can take real-world actions on your behalf. The privacy promises are notable. So are the security questions nobody is asking loudly enough.
Anthropic Says Its Own AI Broke Into Outside Systems, the Fourth Such Case
The company's disclosure points to a January 2026 incident involving an early build of Claude Opus 4.6, deepening questions about what happens when AI agents act on their own.
OWASP Updates Its AI Security Danger List, and the Biggest Threats May Surprise You
The security industry's most-watched ranking of AI software risks has been refreshed with real incident data for the first time. Prompt injection stays at the top, but a newer danger tied to AI agents acting on their own is climbing fast.
A Simple Network Misconfiguration Lets Hackers Quietly Reprogram AI Agents
A flaw in Nvidia's NemoClaw tool means visiting one bad website could hand a stranger permanent control over your AI assistant's instructions, with no warning and no download required.
Hidden Text in Emails Can Trick AI Assistants Into Showing You Fake Numbers
Researchers planted invisible instructions inside ordinary emails and watched an AI summariser rewrite invoice amounts and meeting dates without any warning to the reader.
UAC-0099 Hides a Fake Nuclear Threat in Malware to Break AI Analysis Tools
A Russia-aligned group is stuffing malware with a shock prompt designed to make security analysts' AI assistants refuse to look at the code.
When Your AI Assistant Goes Rogue: What To Do in the First 24 Hours
An hour-by-hour guide for what actually happens when an AI agent starts doing things nobody asked it to do, drawn from real incidents and written for everyone who might be caught in the fallout.
Amazon's Kiro AI Coding Tool Can Be Tricked Into Leaking Your Secrets
Researchers show how a hidden instruction in a project file can turn Amazon's agentic coding assistant into a data-exfiltration channel.
AI Agents Were Tricked Into Attacking Hugging Face Using a Makeshift Message Board
Researchers found that AI agents can be manipulated by fake instructions left in shared spaces. The Hugging Face incident is forcing a rethink of how these systems decide who to trust.