Share story
Science Security

ToFu researchers report security bugs in 343 tools across 118 MCP servers

Researchers behind the ToFu preprint report finding verified security bugs in 343 tools across 118 MCP servers, after evaluating 273 servers containing 3405 tools. Their framework tests whether tools enforce their documented input requirements when software translates an AI model's outputs into tool calls. ToFu derives security checks from tool metadata and a corpus of sanitizers organized by software weakness class. It tailors those checks to individual tools and automatically generates tests that probe their behavior. The researchers say their findings show that tools frequently fail to enforce documented input semantics, making model-generated arguments unsafe to treat as trusted.
Sources
cs.CR updates on arXiv.org
Published by Tech & Business, a media brand covering technology and business. This story was sourced from cs.CR updates on arXiv.org and reviewed by the T&B editorial agent team.
Back to Newswire
Keep reading
Full wire
AI Products
AI Products

Tencent plans about $5 billion bond offering to help fund AI spending

Tencent told fixed-income investors Monday that a planned bond offering of about $5 billion would help finance AI-related capital expenditures, Bloomberg reported, citing people familiar with the matter. The offering would provide...

Bloomberg Technology
Products Security
Products Security

IonQ agrees to acquire Elisity for up to $1.3 billion in stock

Quantum computing firm IonQ has agreed to acquire Elisity for as much as $1.3 billion in an all-stock transaction, Bloomberg reported. The deal is intended to expand IonQ's cybersecurity platform to address dangers assisted by art...

Bloomberg Technology
Security Policy
Security Policy

UK expands AI vulnerability searches into closed government systems

The UK government will expand its use of frontier AI models to find vulnerabilities, moving the next phase into closed government systems. One pilot generated 407 findings across nine government organisations during a month of wee...

The Next Web
AI Infrastructure
AI Infrastructure

AWS launches Ray LLM containers for inference across GPU nodes

AWS has launched Ray LLM Deep Learning Containers for serving language models across multiple GPU nodes, extending its preassembled inference stack beyond single-node deployments. The containers bundle the inference engine, servin...

Artificial Intelligence
Infrastructure AI
Infrastructure AI

Microsoft details 96-chip Maia 300 racks and expanded inference network

Microsoft detailed a Maia 300 design that doubles accelerator density to 96 chips in a 167-kW rack and connects up to 12,288 accelerators through one network. The company says the full rack delivers up to 7 times Maia 200's token ...

azure.microsoft.com