Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

Every so often, an industry gets a moment that quietly redraws where the line is — not because anything was said, but because something was proven. AI security had one of those moments last week, and it's worth being direct about that before getting into the details: this wasn't an incremental data point. It was the moment a risk that security and safety researchers had described in theory for years showed up, fully formed, in a disclosed incident report.

AI pentesting (AI penetration testing) is the use of reasoning-capable AI models to autonomously find, exploit, and validate security vulnerabilities in running applications — especially the context-dependent flaws, such as broken authorization and business-logic abuse, that traditional scanners cannot detect.

Here's a genuinely unsettling way to lose control of your laptop in 2026. You clone a normal-looking repo, ask your AI coding assistant to "set it up," and it writes an attacker's SSH key into your ~/.ssh/authorized_keys -- without ever really telling you that's what it did. No memory corruption, no zero-day, nothing clever. Just a file in the repo that wasn't the file it claimed to be. That attack is real, it's this week's news, and I'll walk through it. But the trick underneath is decades old.

We ran 300 vulnerability-finding scans to measure how repeatable an agentic LLM security review is on the same code, prompt, and harness. The headline result is not that one scanner "wins" a self-referential leaderboard. It is that LLM security findings are unevenly repeatable: reference-matched findings were stable, but extra-model reports varied widely from run to run.

For over twenty years, the global security community has operated under a single, comfortable assumption: that a centralized public source could help track, analyze, and enrich the world’s software vulnerabilities at the pace the industry needed. When the National Vulnerability Database (NVD) was established, the open source vulnerability lifecycle moved at a radically different pace.

As organizations adopt AI agents to build software, security teams face a new challenge: risk is no longer introduced only through the code that gets produced. It emerges continuously through the tools agents use, the actions they take, and the code they generate. This is the problem Evo Agentic Development Security (ADS) was designed to solve. ADS secures all three layers of the agentic development system—what agents use, what they do, and what they generate.

Today, we're announcing Agentic Development Security (ADS), a new Evo solution designed for securing AI-driven software development. AI agents are now active participants in the software development process, selecting tools, executing actions across systems, and generating production-ready code at machine speed.

For years, application security teams have focused on a familiar set of questions: Is the code secure? Are the dependencies vulnerable? Is the build pipeline protected? Are issues being caught before they reach production? Agentic development adds a new question: What systems, tools, instructions, and permissions helped produce this code? AI coding agents are no longer just suggesting snippets or completing lines of code.

Finding issues is easier than ever. Triaging and fixing them is what's scarce. Through Snyk's Secure Developer Program, open source maintainers get the signal to cut through the noise and the platform to fix what matters, free for their open source projects.

An attacker republished the entire @mastra npm scope on June 17, 2026, slipping a single malicious dependency into 143 packages and counting, including @mastra/core, which pulls roughly 4 million downloads a month and has hundreds of dependent projects. The injected dependency, easy-day-js, is a dayjs lookalike whose install hook disables TLS verification, downloads a second-stage payload from a raw IP address, and runs a cross-platform cryptocurrency stealer in the background.