$ winget install --id SST.opencode --exact --version 1.18.7Run in Command Prompt, PowerShell, or Windows Terminal. Prompts for any agreements.
For IT teams
App deployment, patching, and remote support in one place. Push this app to every device you manage, keep it patched automatically, and see new CVEs the moment they land. Works with Intune or fully standalone.
Sign up freeFree for up to 5 devices.
opencode is an AI coding agent built for the terminal. It features:
- A responsive, native, themeable terminal UI.
- Automatically loads the right LSPs, so the LLMs make fewer mistakes.
- Have multiple agents working in parallel on the same project.
- Create shareable links to any session for reference or to debug.
- Log in with Anthropic to use your Claude Pro or Claude Max account.
- Supports 75+ LLM providers through Models.dev, including local models.
Copy a command tailored to that specific architecture, type, and scope - useful when winget would otherwise pick a different default.
25 known CVEs via NVD
Claude Code is an agentic coding tool. From 2.1.38 until 2.1.163, Claude Code's worktree handling allowed creation of worktrees named ".git" and navigation to worktrees outside the sandbox context, enabling git directory confusion attacks. By exploiting symlink manipulation and...
Claude Code is an agentic coding tool. From 2.1.59 until 2.1.128, the Claude Code /copy command wrote responses to a hardcoded, predictable path (/tmp/claude/response.md) without UID isolation, randomness, or symlink protection. The file was created world-readable (0644) in a w...
Claude Code is an agentic coding tool. From 0.2.54 until 2.1.163, because the hostname huggingface.co was pre-approved as a bare hostname for the WebFetch tool, any path on that domain—including attacker-controlled model repositories—was auto-approved without a permission promp...
In versions 2.1.63 through 2.1.83 of Claude Code, the folder trust determination logic used the git worktree commondir file without validating its contents. An attacker could craft a malicious repository with a commondir file pointing to a path the victim had previously trusted,...
Claude Code is an agentic coding tool. Prior to version 2.1.64, Claude Code's sandbox did not prevent sandboxed processes from creating symlinks pointing to locations outside the workspace. When Claude Code subsequently wrote to a path within such a symlink, its unsandboxed proc...
Claude Code is an agentic coding tool. In versions prior to 2.1.75 on Windows, Claude Code loaded the system-wide default configuration from C:\ProgramData\ClaudeCode\managed-settings.json without validating directory ownership or access permissions. Because the ProgramData dire...
Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in authentication helper execution where helper configuration values are executed using shell=true without input validation. Attackers who can influence authentication settings can injec...
Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the prompt editor invocation utility that allows attackers to execute arbitrary commands by crafting malicious file paths. Attackers can inject shell metacharacters such as $() or bac...
See a CVE that affects your fleet? Pckgr RMM flags vulnerable devices and pushes the patched version automatically - automated patching is the only way to keep up.