Docker announced at WeAreDevelopers on September 24 that it is donating its Apache 2.0 Sandbox Kit Specification, now at v3, to the CNCF, packaging an AI agent, its tools, and a typed list of requeste…
Docker released Cloud Sandboxes, hosted microVM-isolated execution environments for AI coding agents that let developers move a sandbox between a laptop and Docker-managed cloud infrastructure with th…
BAND connected its multi-agent collaboration platform to Docker Sandboxes on September 24th, letting a coding agent running beside a developer's local code communicate with hosted agents and people in…
Docker Sandboxes introduce a new trust boundary for AI coding agents by running them inside a microVM with its own kernel and Docker Engine, mediating host access through explicit workspace, credentia…
Docker released Docker Sandboxes 0.42.0 on September 7, 2026, fixing two vulnerabilities — CVE-2026-77179 (Critical) and CVE-2026-79994 (High) — that could let a malicious workload escape its shared-w…
A developer guide details running local LLMs with OpenCode, Ollama, and Docker Sandboxes (sbx) on an Apple MacBook Pro M5 with 48GB of memory, pulling Qwen 3.8 27B mxfp8 (32GB) and Gemma 4 31B mxfp8 (…
The SBX AI Evaluation Kit, an open-source Docker Sandboxes Mixin Kit, enables reproducible AI evaluation workflows by executing configured commands in isolated sandboxes and recording runtime evidence…
Micah Lee, a security researcher, published a technical guide on sandboxing coding agents by creating an isolated SSH agent that loads a dedicated agent-only signing key, preventing agents from access…
GitHub Agentic Workflows (gh-aw) version 0.82.9 added Docker Sandboxes as a supported agent runtime, allowing AI coding agents in GitHub Actions to run Docker containers and execute arbitrary commands…
Palo Alto Networks found machine identities now outnumber humans 109 to 1, with roughly 79 in every 100 being AI agents, and 37% of organizations can revoke an agent's credentials while 30% have immut…
On January 14, 2026, Pillar Security disclosed CVE-2026-22708, a high-severity flaw in Cursor that allowed shell built-ins like export, typeset, and declare to execute without appearing in the allowli…
A new guide outlines five practical steps to secure software supply chains, including sandboxing AI agents with Docker Sandboxes, freezing dependencies with a five-day cooldown, using hardened multi-s…
A developer introduced SIP, a set of five immediate software supply chain controls for technical leaders, covering AI agent isolation, dependency freezing, hardened container builds, SBOM generation, …
Docker Sandboxes now allow Claude Code and Codex coding agents to run with full autonomy inside isolated microVMs, reducing the risk of granting --dangerously-skip-permissions or --dangerously-bypass-…
Docker Sandboxes is a local developer-workstation tool that mounts the user's filesystem and runs microVMs on their own hardware, while E2B and Cloudflare Sandbox SDK are cloud-hosted, API-driven serv…
Docker Inc. launched Docker Sandboxes, a new product that isolates AI coding agents in microVMs with their own kernels and private Docker daemons, rather than containers, to make bypass-mode agents sa…
Docker announced general availability of Docker Sandboxes on January 30, 2026, a microVM-based runtime for AI coding agents that wraps tools like Claude Code in disposable environments with a credenti…
A security analysis of Docker Sandboxes v0.37.1 reveals that the default 'Balanced' network profile allows egress to any subdomain of wildcard domains like *.amazonaws.com, *.githubusercontent.com, an…
Docker's sandbox kits, defined in spec.yaml files, let developers pre-configure isolated environments with tools, network rules, and credential proxying, reducing setup friction that otherwise pushes …
At AI DevCon London, a Docker engineer demonstrated why prompt-level guardrails are insufficient for coding agents, advocating for isolated microVM environments like Docker Sandboxes. The talk highlig…