Heidelberg AI News
All stories
8 stories from Docker
Thursday 29 October
OfficialDocker
Coding Agent Horror Stories: The CVE That Did Not Exist
An official Docker video describes a case in which an AI code review agent invented a CVE that did not exist and recommended dangerous fixes. It explains how Docker Sandboxes contain agents and why their output needs verification.
Wednesday 28 October
OfficialDocker
Win the Agentic Era, Together: Introducing the Docker Navigator Partner Program
Docker is launching the Navigator Partner Program, structured in three tiers, offering co-selling benefits and a new incentive for every registered AI governance deal.
Thursday 22 October
OfficialDocker
ActiveState Partners with Docker to Secure the Open Source in Enterprise Containers
ActiveState has partnered with Docker to help secure open source components used in enterprise containers. The collaboration addresses container security across the image, build, and runtime stages, offering practical steps to reduce the attack surface and prevent vulnerabilities from reaching production.
Wednesday 21 October
OfficialDocker
Your Agent Runs in a Docker Sandbox. Now It Can Join a Team.
Docker's official channel announces that AI agents running in Docker Sandboxes can now join a team, allowing isolated agents to collaborate across environments and manage access securely, using BAND AI.
OfficialDocker
From baseline to Secure Software Factory: securing the systems that build your software
In July, Docker, Snyk, and Keycard published Agent Baseline, an open, vendor-neutral reference architecture that defines security outcomes for running AI agents in the enterprise. The initiative grew out of conversations with industry leaders who want to adopt agents more broadly but need answers to questions about what agents are operating with what capabilities and whether they remain secure.
Wednesday 14 October
OfficialDocker
Harbor + Docker Sandboxes: Run Safe, Reproducible Agent Evals
Docker's Harbor can now run every eval task in Docker Sandboxes, which are MicroVM environments for running agents like Claude Code, Codex, and Cursor safely. With Sandboxes you can define custom network policies for fair, reproducible evals, and you can run evals locally or in the cloud, starting free on Docker Sandboxes on local surfaces and scaling up.
Thursday 1 October
OfficialDocker
Trust Docker for the agents you don't
At the WeAreDevelopers event, Docker introduced Cloud Sandboxes, an open Sandbox Kit specification, and a commitment to bring Kits to the CNCF for neutral governance. The offering is framed around running agents that users do not fully trust.
Thursday 3 September
OfficialDocker
YOLO Mode: Agent Autonomy Without the Guardrails
Docker explains that unrestricted coding-agent autonomy can put files, credentials and networks at risk, and says isolated disposable sandboxes reduce the blast radius.