Xygeni Blog

AI agent security: know every agent, catch the risk, guard what it installs

AI agents don't just answer, they act: they call tools, hold credentials and install packages on their own. Here is how AI agent security works in four steps, from an inventory of every agent in your code to guarding what agents install.
10 min read

API security testing: build your API inventory from code, then test it at runtime

The OWASP Agentic AI Top 10 names the ten ways AI agents fail. Here is what ASI01 to ASI10 actually mean in a real pipeline, where each risk gets in, and which ones you can stop before deploy.

PHP2Shell to Node2Shell: Five Supply Chain Security Controls

October’s incidents showed the next CVE or supply chain worm can hit any ecosystem. Docker Captain Mohammad-Ali A’rĂ¢bi shares five controls, from sandboxed AI agents to enforceable release checks, to get ready before it happens.

Who Decided That Release Could Ship? AI Coding Agent Security Lessons from ENISE 2026

At ENISE 2026, Xygeni CEO JesĂºs Cuadrado showed how one sentence in a GitHub issue led to an unauthorized release, and left CISOs with four questions about AI coding agents.

OWASP Agentic AI Top 10 Explained: ASI01–ASI10

The OWASP Agentic AI Top 10 names the ten ways AI agents fail. Here is what ASI01 to ASI10 actually mean in a real pipeline, where each risk gets in, and which ones you can stop before deploy.
11 min read

Model Extraction Attack: Why Inventory Comes First

A model extraction attack lets an attacker copy your model one query at a time, with no breach and no stolen file. Here is how model stealing works, and why the first defense is knowing every inference endpoint you expose.

Agentic AI risk and blast radius: limit the agent, or recover faster?

Constrain the agent, recover faster, or contain it from below? Three practitioners, three answers, and one minimum they all agreed on.
13 min read

npm Supply Chain Security: your vulnerability scanner is looking for the wrong thing

Your npm vulnerability scanner checks for known flaws. Malicious packages have none. Here's what npm supply chain security needs in 2026.

Agent harness engineering: the model isn’t the attack surface, the harness is

Agent harness engineering turns models into useful agents. It also hands attackers a new target: the files that tell your agent what it can do.

NIST Risk Management Framework: Where Your AppSec Program Fits In

The NIST risk management framework is a process, not a checklist. Where AppSec fits in it, which NIST frameworks plug in, and how to feed it evidence.

OWASP ASVS: How to Benchmark Your AppSec Program Against It

OWASP ASVS turns 18. How teams really use it, where adoption breaks, and how to benchmark your AppSec program against it, level by level.

Privilege Escalation Vulnerability in CI/CD pipelines

A privilege escalation vulnerability in CI/CD pipelines needs no exploit. How attackers abuse tokens, triggers, and containers, and how to close each path.
10 min read