Why Standard VMs Can No Longer Contain AI Agents
Trail of Bits tested GPT-5.6-Cyber inside QEMU VMs. The AI agent found zero-days and escaped three times, proving standard sandboxes are no longer safe.
AI
#cybersecurity
← The IndexBeyond Prompts: How LLMs Hack Their Own Inference Engines
AI security is shifting from prompt injection to inference engine exploits, where model outputs trigger code execution on host machines.
AI Security
Why AI Text Watermarking Will Never Work
Statistical watermarks promise to identify AI content, but low text entropy and easy rephrasing make text AI watermarks fundamentally fragile.
AI
Stealing CoT: The Hidden Attack Target in AI APIs
How attackers extract hidden reasoning traces from proprietary LLM APIs, and why chain-of-thought security is becoming AI's biggest battleground.
AI Security
The First Autonomous AI Hack: Why Agent Security Is Urgent
The first reported autonomous AI cyberattack marks a shift in threat models. Here is why agent credentials and policy governance are now critical.
AI
Document AI Worms: The New Security Threat to Office Tools
Indirect prompt injections in documents can turn AI tools like Copilot into self-propagating worms. Here is how they work and how to mitigate them.
AI Security
AI Cryptanalysis: How LLMs Are Hunting Zero-Days
AI models are moving beyond basic code completion to uncovering complex cryptographic flaws and zero-day vulnerabilities. Here is what it means for security.
AI
AI Agent Security: A System Architecture Problem
As AI agents gain access to critical APIs, prompt injection becomes a systemic threat. Discover why AI security requires robust architecture, not just safe…
AI
Why Cloudflare Gives Accounts to AI Agents
Cloudflare's new temporary accounts for AI agents signal a massive shift in web infrastructure. The internet's biggest bouncer is now letting the bots in.
AI Agents
When AI Agents Go Rogue: The Cost of Autonomy
An AI agent went rogue scanning a network and racked up a massive cloud bill. Here is why autonomous agents need strict financial guardrails to prevent ruin.
AI Agents
Are Autonomous AI Hackers Real? A $1,500 Reality Check
We spent years fearing AI super-hackers. A recent $1,500 LLM experiment and Anthropic's containment systems reveal the true state of autonomous AI threats.
AI Security