Security Research

Deep dives into AI agent vulnerabilities, MCP exploits, and defense strategies.

98% Accurate and Still Broken
Research

98% Accurate and Still Broken

We built a 98% accurate classifier. Here's why that number doesn't mean what you think it means.

Steven Jung
Steven Jung·
The Hidden Risk in Notion 3.0 AI Agents: Web Search Tool Abuse for Data Exfiltration
Vulnerability Research

The Hidden Risk in Notion 3.0 AI Agents: Web Search Tool Abuse for Data Exfiltration

A critical security vulnerability in Notion 3.0's AI Agents demonstrates how the combination of LLM agents, tool access, and long-term memory creates exploitable attack vectors for data exfiltration.

Abi Raghuram
Abi Raghuram·
Shopify Exploit: Manipulating Shoppers
MCP Security

Shopify Exploit: Manipulating Shoppers

A critical vulnerability in Shopify's MCP allows attackers to manipulate consumer purchasing decisions using malicious prompts in product descriptions.

Abi Raghuram
Abi Raghuram·