Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

armo

Types of AI Agent Attacks: A Security Team's Taxonomy

May 30, 2026 By Ben Hirschberg In ARMO
A security team running agents in production can already list the ways those agents get attacked: prompt injection, memory poisoning, tool abuse, model tampering, agent-to-agent coercion. The list is not the problem. The problem is that a security architect can recite all five and still not know which ones their detection stack will catch, because the way the field catalogs these attacks says nothing about whether the attack is catchable.
Read Post
armo

The AI Agent Attack Kill Chain: Which Stages You Can Actually Detect

May 30, 2026 By Shauli Rozen In ARMO
The early stages of an AI agent attack are silent. The poisoning, the hijacked intent, the reconnaissance: none of it executes, so none of it produces a runtime signal, and the kill-chain instinct every security team runs on says exactly the wrong thing here: break the earliest link. There is no early link to break. You cannot detect a stage that emits nothing.
Read Post
armo

Tool Call Analysis for AI Attack Detection: Reading What Rides Inside the Call

May 30, 2026 By Yossi Ben Naim In ARMO
A compromised agent doesn’t make a single call it isn’t allowed to make. It queries a table it’s authorized to read, calls a tool it’s authorized to use, sends to a domain that’s on the allowlist. Every call is legal. The attack is in the values it passes, and your tool-call log records all of it as a clean day’s work. A tool call has two layers. Almost every tool you run reads the first one: the call itself: which tool, in what order, at what rate.
Read Post
armo

How to Tell If Your AI Agent Has Been Compromised (When Every Symptom Looks Normal)

May 30, 2026 By Ben Hirschberg In ARMO
Your AI agent just did something it has never done. It called a tool that is not in its usual set, or it opened a connection to a destination you do not recognize, or its output came back subtly wrong. So you do what anyone does: you search for what a compromised agent looks like, and you find a checklist. Unusual tool usage. Unexpected data access. Out-of-context responses. Elevated resource consumption.
Read Post
armo

Detecting AI Agent Lateral Movement in Kubernetes

May 29, 2026 By Yossi Ben Naim In ARMO
An AI agent moving laterally through a Kubernetes cluster does not look like an intrusion. There is no foreign process, no exploit, no dropped binary — just the agent using the identity, network routes, and tools it was handed at deployment to reach targets it was technically allowed to touch. That is the entire problem. The controls you run were built to catch an outsider pivoting from host to host.
Read Post
armo

Commercial vs Open Source AI Attack Detection Tools: A Buyer's Guide

May 29, 2026 By Shauli Rozen In ARMO
If you’re weighing open source against commercial tools for detecting attacks on your AI agents, you’re probably trying to answer a single question. Can we build this ourselves, or should we buy it? It’s a fair question, and the existing content on it isn’t much help. Most comparisons line up tools side by side and tally features. That tells you which tool is better at one slice of the problem. It doesn’t tell you whether you have a working detection program.
Read Post
teleport

What SPIFFE Answers for Workload Identity and What It Doesn't

May 29, 2026 By Rob Cobbins In Teleport
On workload identity, a spec the industry has already started building around, and what the next layer looks like. I don't have a better answer than SPIFFE (Secure Production Identity Framework for Everyone) for workload identity, and that's where I want to start, because what follows is going to sound like I do.
Read Post
DevOps Vulnerabilities Hit 236, With 59% Rated High or Critical Severity

DevOps Vulnerabilities Hit 236, With 59% Rated High or Critical Severity

May 28, 2026 By GitProtect In GitProtect
Major DevOps platforms patched 236 vulnerabilities in 2025, with nearly 60% classified as high or critical severity. According to the latest "DevOps Threats Unwrapped Report," critical flaws surged by 76% ifrom Q1 to Q4, signaling growing pressure on software supply chain security.
Read Post

New in ggshield 1.51: Codex Hooks, MCP Discovery, and SLSA Provenance

May 28, 2026 By GitGuardian In GitGuardian
ggshield 1.51 is here with better support for AI-powered development and browser-less environments. This release adds Codex hook support, MCP server detection across Claude and Cursor, and `ggshield auth login --method oob` for SSH sessions and headless servers. It also strengthens trust in the ggshield supply chain with GitHub Artifact Attestations for release binaries, improves plugin management through your authenticated GitGuardian instance, adds a `vscode` alias for Copilot hook installation, and shows workspace ID in `ggshield api-status`.
View Video

Copyright © 2026 OpsMatters™. All rights reserved.