2025-07-29
Exposing Novel Prompt Injection Vulnerabilities, “Toxic Flows,” in Agentic Systems
We present the toxic flow analysis (TFA) framework to...
Blog
News and Insights from the Invariant team.
2025-06-24
Snyk Acquires Invariant Labs to Accelerate Agentic AI Security Innovation
Acquisition Deepens Snyk Labs Research Bench
2025-05-26
GitHub MCP Exploited: Accessing private repositories via MCP
We showcase a critical vulnerability with the official GitHub MCP server,...
2025-04-29
Invariant Research wins first prize of Center for AI Safety competition
AgentDojo wins $50,000 prize in the SafeBench competition, hosted...
2025-04-24
Announcing our partnership with Smithery
Invariant MCP-Scan is now protecting Smithery
2025-04-17
Introducing Guardrails: The contextual security layer for the agentic era
We are releasing Invariant Guardrails, our state-of-the-art...
2025-04-11
Introducing MCP-Scan: Protecting MCP with Invariant
Today we are launching MCP-Scan, a security scanner designed to protect your agentic...
2025-04-07
WhatsApp MCP Exploited: Exfiltrating your message history via MCP
This blog post demonstrates how an untrusted MCP server can attack and...
2025-04-01
MCP Security Notification: Tool Poisoning Attacks
We have discovered a critical vulnerability in the Model Context Protocol (MCP) that...
2025-03-06
Invariant Gateway: A Seamless Debugging and Security Layer for Agentic Applications
Today, we are releasing Invariant Gateway, a seamless...
2025-01-24
Enhancing Browser Agent Safety with Guardrails
We introduce a novel approach to enhance the safety of browser agents and deploy it as...
2024-12-23
Santa's Agent Challenge
Participate in Invariant's festive Winter Challenge. Can you fix Santa's agent to deliver all the presents?
2024-12-17
Releasing Explorer & Testing: Visualize and Understand AI agents
We are open sourcing Explorer, an observability tool to analyze agent...
2024-12-11
AgentDojo: Jointly evaluate security and utility of AI agents
We release AgentDojo, a new framework for benchmarking the utility and...
2024-10-08
Cracking the Code: Insights from players hacking our agent in the CTF
We share insights from running the first Invariant CTF challenge.
2024-08-12
ETH Spin-Off
Invariant Labs now is an official ETH Zurich Spin-Off
2024-08-05
Fool an Agent to Extract the Secret Password
Participate in the Invariant Summer '24 CTF Challenge to secure autonomous AI systems by...
2024-07-25
Agents with Formal Security Guarantees
We propose a system that imposes hard constraints on AI agents and formally guarantees their security.
2024-07-10
What we've learned from analyzing hundreds of AI web agent traces
We discover, analyze and fix web agent failures in hundreds of traces,...