#LLM security
17 stories taggedLLM security.
When AI Agents Go Rogue: What the Hugging Face Incident Tells Us About Securing AI Systems
Security researcher Adam Shostack watched OpenAI's Black Hat presentation on AI models that started secretly passing messages to each other during training. His verdict: the real problem isn't the AI. It's the missing guardrails around it.
Your AI Safety Certificate Is Worthless the Moment the Agent Goes Live
Compliance badges on AI products look reassuring. They don't protect you once an autonomous agent starts reading your files, calling your internal systems, and making decisions faster than any human can watch.
Five Major AI Coding Tools Keep Inventing the Same Fake Software Packages
A researcher found 127 made-up package names shared across ChatGPT, Claude, Gemini, and DeepSeek, and 53 of those names are still free for criminals to register today.
Fake Files That Stop Hackers: How 'Context Bombs' Crash AI Attack Agents
A security firm has found a way to halt automated AI attacks in their tracks by planting decoy text that triggers the safety rules built into AI systems. Success rates for AI-driven hacks dropped by up to 90% in tests.
A Russian-speaking hacker turned Google's Gemini CLI into his botnet co-pilot
For roughly a year, an attacker chatted with Google's open-source AI tool to run malware on eight computers inside a dental clinic, migrate his servers, and troubleshoot bugs in six minutes flat.
One Poisoned Email Can Rewrite What Your AI Assistant 'Remembers' About You
Researchers show how a single message can plant a false memory in an AI agent's long-term store, quietly steering its answers in every future chat.
AI Agents Can Be Tricked Into Sending Money. Zscaler Has the Data.
A new study shows that some expensive, enterprise-grade AI assistants fall for hidden instructions that most humans would ignore, and experts warn the real danger is far bigger than a fake three-dollar fee.
Context Manipulation Attack 'BioShocking' Turns Agentic Browsers Into Credential Thieves
Researchers demonstrate how feeding poisoned context to AI-driven browser agents causes them to quietly drop safety guardrails and exfiltrate stored credentials.
North Korean Malware Tells AI Analyzers to Look Away
A macOS sample attributed to Pyongyang-linked actors contains prompts designed to make LLM-assisted security tools abandon their analysis. Defenders are starting to notice the pattern.
AI Agents Are Being Manipulated Through the Data They Trust
Hidden content injections and context poisoning are turning autonomous AI pipelines into attack surfaces. Here's what defenders need to understand before deploying agents at scale.
AI-SPM Is Now a Real Category. Here's Why Your Organization Probably Needs It.
More than half of enterprise AI agents run without security oversight or logging. A maturing class of AI security posture management tools exists to fix that — if you know what to look for.
AI Web Agents Have No Reliable Prompt Injection Defenses, Benchmark Finds
Researchers ran 3,168 adversarial tests against GPT-5 and Gemini-powered agents. The 'Robust Behavior' outcome — agent completes task, attacker gets nothing — never appeared.
AI Red Teaming Grew Up. The Job Description Is Still Being Written.
The tools broke when LLMs arrived. Now the discipline is rebuilding itself in real time — and the threat model includes teenagers with too much free time.
A Free LLM, a Custom Harness, and 27 Compromised VMs: The AI Worm You Don't Need a Lab to Build
University of Toronto researchers built a self-replicating AI worm using only locally-hosted open models. It spread to 82% of its targets. The threat model here isn't frontier AI — it's the misconfigured server you forgot about.
OpenAI's Lockdown Mode Admits the Problem It Can't Quite Fix
The new containment feature reduces AI-enabled data exfiltration — it doesn't stop it. Experts are divided on whether enterprises should even trust a vendor to police itself.