Agentic AI at risk after MCP design flaw discovery? #ai #cybersecurity #podcast

Apr 21, 2026 By LimaCharlie In LimaCharlie
In this week's Intel Chat, Chris Luft and Matt Bromiley discuss a design flaw in Anthropic's Model Context Protocol (MCP) that could enable large-scale supply chain attacks on agentic AI systems. Researchers at OX Security found that MCP's command execution allows malicious commands to run silently without sanitization checks or warnings.
View Video
jfrog

Unlock the Power of Agents with JFrog's Skills and MCP Tools

Apr 21, 2026 By Lavanya Chockalingam In JFrog
Agents are writing code, suggesting dependencies, and reviewing PRs, without any knowledge about your trusted package sources, security posture, or governance policies. When agents operate without supply chain context, they introduce risk, create rework, and weaken the guardrails DevSecOps teams rely on to ship with confidence. JFrog is changing that.
Read Post
LimaCharlie

When Claude Code Hunts Cobalt Strike: Agentic Security Operations in Action

Apr 21, 2026 By Daniel Ballmer In LimaCharlie
Security teams enter an asymmetric battle when adversaries freely use AI to wage attacks. The aggressors are armed with top-tier capabilities. Defenders hesitate to adopt AI they can't see, trust, or control. SecOps teams are drowning in alerts and outpaced by adversaries who are unafraid to automate everything. The solution isn't another dashboard or another AI chatbot offering recommendations.
Read Post
veracode

Application Security Prioritization: How the Best Teams Fix What Matters Most

Apr 21, 2026 By Natalie Tischler In Veracode
In the race to ship software faster, security teams are drowning. Not in vulnerabilities… those are abundant, predictable even. They’re drowning in noise. The average enterprise application generates thousands of security findings from multiple scanners, each screaming for attention with equal urgency. Meanwhile, developers are building faster than ever, fueled by cloud-native architectures, open-source dependencies, and AI-generated code. The uncomfortable truth?
Read Post
persona

Building Know Your Agent: The missing identity layer for agentic commerce

Apr 21, 2026 By Tim Williams In Persona
AI agents are being deployed in the real world at pace. In the enterprise realm, they’re accessing APIs, shipping code, and running decisioning workflows on behalf of the organizations and individuals who deploy them. Entirely new businesses have sprung up, leveraging AI agents to streamline customer support and sales processes.
Read Post
CrowdStrike

Introducing the CrowdStrike Shadow AI Visibility Service

Apr 21, 2026 By JJ Cranford - Kris Krewson In CrowdStrike
Since the launch of CrowdStrike AI Security Services in 2025, our Professional Services team has yet to encounter an organization with an accurate inventory of the AI tools and services in use across its environment. One customer counted 150 agents in its inventory. We found over 500. Another had not approved agentic development at all; we discovered over 70 active agents.
Read Post
teleport

Reverse Proxy: How It Works & Example Architecture

Apr 21, 2026 By Peter ONeill In Teleport
Accessing modern infrastructure requires more than a network-level foothold. As services spread across clouds, clusters, and regions, the question of who can reach what stops being a network question and becomes an identity question. Reverse proxies are the component that answers it. A reverse proxy sits between clients and backend services, validating identity and enforcing authorization on every inbound request before any application is touched.
Read Post
netwrix

Managing the non-human identity lifecycle in modern environments

Apr 21, 2026 By Dirk Schrader In Netwrix
Non-human identities (NHIs) such as service accounts, API keys, tokens, and workload identities now outnumber human users by 10x or more in most organizations. Unlike human identities that follow HR-driven lifecycles, NHIs are often created ad hoc, granted excessive permissions, and rarely decommissioned. Effective NHI lifecycle management spans five stages: discovery and inventory, secure provisioning, ongoing monitoring, credential risk management (including rotation), and decommissioning.
Read Post

The Three-Layer Strategy for Autonomous Agent Governance with Joe Hladik and Amit Malik

Apr 21, 2026 By Rubrik In Rubrik
The race for AI dominance has created a dangerous imbalance between business velocity and cyber resilience. In this episode, host Caleb Tolin is joined by ⁠Joe Hladik⁠, Head of ⁠Rubrik⁠ Zero Labs, and Staff Security Researcher ⁠Amit Malik⁠ to break down the findings of their latest report on agentic adoption. The discussion centers on the Agentic Paradox. This is the technical reality that tools designed to automate high-level tasks are inherently built to find the most efficient path around obstacles, including existing security policies.
View Video
Subscribe to Security

Copyright © 2026 OpsMatters™. All rights reserved.