Agentic traffic is rising. Here's why AI gateways are key to securing outbound API calls made by autonomous agents.| Nordic APIs
Why you should never trust your inference layer to enforce security policies and always enforce row-level access control (RLAC) for LLM database access.| www.tinybird.co
This is long compilation of all the recorded MCP security flaws in the wild.| composio.dev
I gave a talk on Wednesday at the Bay Area AI Security Meetup about prompt injection, the lethal trifecta and the challenges of securing systems that use MCP. It wasn’t …| Simon Willison’s Weblog
Securing agentic systems requires rethinking everything from authentication to observability. A new playbook is emerging: security for agents.| Menlo Ventures
What is Context Engineering?| ShiftMag
Model Context Protocol (MCP) use is increasing in popularity for connecting AI agents to data sources, and other services. But so too are vulnerabilities that bring unique risks to agentic systems.| CSO Online
The Good, the Bad, and the Ugly of AI’s interface to the real world.| blog.stackaware.com
In this post we look at the new Prompt Guard 2 model from Meta, and introduce a concept I've been calling "Tokenization Confusion" which aims to confuse Unigram tokenization into generating tokens which will result in the misclassification of malicious prompts. We'll also look at why building up our ML knowledge will lead to better findings when assessing LLM API’s, as I discovered during a flight across the Atlantic.| XPN InfoSec Blog
A team of researchers at Invariant Labs, based in Zurich, Switzerland, has warned developers of a prompt injection […]| DEVCLASS
GitHub's official MCP server grants LLMs a whole host of new abilities, including being able to read and issues in repositories the user has access to and submit new pull …| Simon Willison’s Weblog