Avatar

Sanket Mendapara

Security Research Engineer

AI Software and Platform

Sanket Mendapara is an AI Security Research Engineer in Cisco’s AI Software & Platform group, where he is part of the AI Defense Threat Research & Security team. His work focuses on advancing the security of generative and agentic AI systems through AI red teaming, agentic security analysis, AI runtime defenses, threat intelligence, and the development of open-source security and assessment tools. Prior to Cisco, Sanket had been part of the Threat Research teams at Armorblox, Sophos, and Cequence Security, where he worked across email security, endpoint protection, malware analysis, spam detection, and large-scale threat intelligence programs. His experience spans both traditional cybersecurity and emerging AI-driven attack surfaces, giving him a comprehensive perspective on securing modern AI systems.

December 22, 2025

ARTIFICIAL INTELLIGENCE - AI

Cisco’s MCP Scanner Introduces Behavioral Code Threat Analysis

4 min read

A model context protocol (MCP) tool can claim to execute a benign task such as “validate email addresses,” but if the tool is compromised, it can be redirected to fulfill ulterior motives, such as exfiltrating your entire address book to an external server. Traditional security scanners could flag suspicious network calls or dangerous functions and […]

December 9, 2025

1

ARTIFICIAL INTELLIGENCE - AI
Vineeth Sai Narajala
Sanket Mendapara

Securing AI Agents with Cisco’s Open-Source A2A Scanner

3 min read

The Rise of Agent Networks: A New Security Frontier  Emerging Agent-to-Agent (A2A) frameworks have emerged to support organizations as they move from isolated AI applications to interconnected networks of autonomous agents. A2A enables software agents to discover, authenticate, and collaborate across organizational boundaries, unlocks unprecedented automation capabilities. A2A also introduces an expanded attack surface, and […]