AI Agent Security Risks: What Can Go Wrong When Agents Act on Their Own
Learn the top AI agent security risks, from prompt injection to excessive autonomy and credential exposure, and how to contain them.
Docker Blog Articles
Updated just now · 10 articles from Docker Blog
Docker Hub security advisory: personal access tokens transferred during account-to-organization conversions
CVE-2026-105445: Docker Hub account conversion could re-assign personal access tokens to a new owner. Read what happened, who was affected, and the fix.
Trust Docker for the agents you don’t
At WeAreDevelopers, Docker introduced Cloud Sandboxes, the open Sandbox Kit specification, and a commitment to bring Kits to the CNCF for neutral governance.
Manufacturing Trust for AI Agents | Docker’s WeAreDevelopers Keynote
Docker's WeAreDevelopers keynote shows how Sandboxes, Kits, and Cloud Sandboxes give AI agents strong isolation and reproducible authority.
From Dockerfile to Kit: the Docker Sandboxes Kit Specification
Docker's Sandbox Kit Specification v3 packages an AI agent's network rules, credentials, and volumes as an ordinary, pinnable OCI image.
Docker and CNCF partner on an open spec for agent permissions
Docker is bringing the open source Sandbox Kit Spec to the CNCF, so AI agent permissions become a neutral, vendor independent standard built on OCI.
Ad
Introducing Cloud Sandboxes: Start on Your Laptop, Finish in the Cloud
Run agents on your laptop, in the cloud, and move between them with one command, all safely. Earlier this year we launched Docker Sandboxes: microVM environm...
Meet the Ecosystem: Partners and Customers at WeAreDevelopers with Docker
Meet the partners and customers bringing practical AI, security, and development sessions to the Docker Pavilion at WeAreDevelopers. The post explains why a ...
6 Benefits of Sandbox Environments (and How Docker Sandboxes Delivers Them)
Learn about the key benefits of sandbox environments with Docker including isolation, definable controls, secrets credential handling, and more.
YOLO Mode: Agent Autonomy Without the Guardrails
YOLO mode lets an AI agent run without asking permission. Learn what it is, why it's risky, and how to run it safely.
