An architectural deep dive into Agentic AI vulnerabilities. Learn how attackers exploit the Model Context Protocol (MCP) to achieve Remote Code Execution (RCE) via tool calling hijacks.
A technical deep dive into how attackers exploit Agentic AI network tools to achieve Server-Side Request Forgery (SSRF), steal AWS/GCP cloud credentials, and bypass naive IP filters via TOCTOU DNS Rebinding.
Analyzing the risks of malicious macros and DDE payloads hidden in tabular data, and how they compromise Data Scientists and AI Agents.