Parse args in the @packages/opencode/bwrap.sh script to select a project directory to run opencode in.
Parsing bwrap.sh args for project dir
How would you configure this sandbox, based on the following mechanisms of sandboxing:
Anthropic Sandbox Runtime (srt)
A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.
srt uses native OS sandboxing primitives (sandbox-exec on macOS, bubblewrap on Linux) and proxy-based network filtering. It can be used to sandbox the behaviour of agents, local MCP servers, bash commands and arbitrary processes.
Beta Research Preview
The Sandbox Runtime is a research preview developed for Claude Code to enable safer AI agents. It's being made available as an early open source preview to help the broader ecosystem build more secure agentic systems. As this is an early research preview, APIs and configuration formats may evolve. We welcome feedback and contributions to make AI agents safer by default!
Installation
npm install -g @anthropic-ai/sandbox-runtime
Basic Usage
# Network restrictions
$ srt "curl anthropic.com"
Running: curl anthropic.com
<html>...</html> # Request succeeds
$ srt "curl example.com"
Running: curl example.com
Connection blocked by network allowlist # Request blocked
# Filesystem restrictions
$ srt "cat README.md"
Running: cat README.md
# Anthropic Sandb... # Current directory access allowed
$ srt "cat ~/.ssh/id_rsa"
Running: cat ~/.ssh/id_rsa
cat: /Users/ollie/.ssh/id_rsa: Operation not permitted # Specific file blocked
Overview
This package provides a standalone sandbox implementation that can be used as both a CLI tool and a library. It's designed with a secure-by-default philosophy tailored for common developer use cases: processes start with minimal access, and you explicitly poke only the holes you need.
Key capabilities:
- Network restrictions: Control which hosts/domains can be accessed via HTTP/HTTPS and other protocols
- Filesystem restrictions: Control which files/directories can be read/written
- Unix socket restrictions: Control access to local IPC sockets
- Violation monitoring: On macOS, tap into the system's sandbox violation log store for real-time alerts
Example Use Case: Sandboxing MCP Servers
A key use case is sandboxing Model Context Protocol (MCP) servers to restrict their capabilities. For example, to sandbox the filesystem MCP server:
Without sandboxing (.mcp.json):
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem"]
}
}
}
With sandboxing (.mcp.json):
{
"mcpServers": {
"filesystem": {
"command": "srt",
"args": ["npx", "-y", "@modelcontextprotocol/server-filesystem"]
}
}
}
Then configure restrictions in ~/.srt-settings.json:
{
"filesystem": {
"denyRead": [],
"allowWrite": ["."],
"denyWrite": ["~/sensitive-folder"]
},
"network": {
"allowedDomains": [],
"deniedDomains": []
}
}
Now the MCP server will be blocked from writing to the denied path:
> Write a file to ~/sensitive-folder
✗ Error: EPERM: operation not permitted, open '/Users/ollie/sensitive-folder/test.txt'
How It Works
The sandbox uses OS-level primitives to enforce restrictions that apply to the entire process tree:
- macOS: Uses
sandbox-execwith dynamically generated Seatbelt profiles - Linux: Uses bubblewrap for containerization with network namespace isolation
Dual Isolation Model
Both filesystem and network isolation are required for effective sandboxing. Without file isolation, a compromised process could exfiltrate SSH keys or other sensitive files. Without network isolation, a process could escape the sandbox and gain unrestricted network access.
Filesystem Isolation enforces read and write restrictions:
- Read (deny-only pattern): By default, read access is allowed everywhere. You can deny specific paths (e.g.,
~/.ssh). An empty deny list means full read access. - Write (allow-only pattern): By default, write access is denied everywhere. You must explicitly allow paths (e.g.,
.,/tmp). An empty allow list means no write access.
Network Isolation (allow-only pattern): By default, all network access is denied. You must explicitly allow domains. An empty allowedDomains list means no network access. Network traffic is routed through proxy servers running on the host:
Linux: Requests are routed via the filesystem over a Unix domain socket. The network namespace of the sandboxed process is removed entirely, so all network traffic must go through the proxies running on the host (listening on Unix sockets that are bind-mounted into the sandbox)
macOS: The Seatbelt profile allows communication only to a specific localhost port. The proxies listen on this port, creating a controlled channel for all network access
Both HTTP/HTTPS (via HTTP proxy) and other TCP traffic (via SOCKS5 proxy) are mediated by these proxies, which enforce your domain allowlists and denylists.
For more details on sandboxing in Claude Code, see:
- Claude Code Sandboxing Documentation
- Beyond Permission Prompts: Making Claude Code More Secure and Autonomous
Architecture
src/
├── index.ts # Library exports
├── cli.ts # CLI entrypoint (srt command)
├── utils/ # Shared utilities
│ ├── debug.ts # Debug logging
│ ├── settings.ts # Settings reader (permissions + sandbox config)
│ ├── platform.ts # Platform detection
│ └── exec.ts # Command execution utilities
└── sandbox/ # Sandbox implementation
├── sandbox-manager.ts # Main sandbox manager
├── sandbox-schemas.ts # Zod schemas for validation
├── sandbox-violation-store.ts # Violation tracking
├── sandbox-utils.ts # Shared sandbox utilities
├── http-proxy.ts # HTTP/HTTPS proxy for network filtering
├── socks-proxy.ts # SOCKS5 proxy for network filtering
├── linux-sandbox-utils.ts # Linux bubblewrap sandboxing
└── macos-sandbox-utils.ts # macOS sandbox-exec sandboxing
Usage
As a CLI tool
The srt command (Anthropic Sandbox Runtime) wraps any command with security boundaries:
# Run a command in the sandbox
srt echo "hello world"
# With debug logging
srt --debug curl https://example.com
# Specify custom settings file
srt --settings /path/to/srt-settings.json npm install
As a library
import {
SandboxManager,
type SandboxRuntimeConfig,
} from '@anthropic-ai/sandbox-runtime'
import { spawn } from 'child_process'
// Define your sandbox configuration
const config: SandboxRuntimeConfig = {
network: {
allowedDomains: ['example.com', 'api.github.com'],
deniedDomains: [],
},
filesystem: {
denyRead: ['~/.ssh'],
allowWrite: ['.', '/tmp'],
denyWrite: ['.env'],
},
}
// Initialize the sandbox (starts proxy servers, etc.)
await SandboxManager.initialize(config)
// Wrap a command with sandbox restrictions
const sandboxedCommand = await SandboxManager.wrapWithSandbox(
'curl https://example.com',
)
// Execute the sandboxed command
const child = spawn(sandboxedCommand, { shell: true, stdio: 'inherit' })
// Handle exit
child.on('exit', code => {
console.log(`Command exited with code ${code}`)
})
// Cleanup when done (optional, happens automatically on process exit)
await SandboxManager.reset()
Available exports
// Main sandbox manager
export { SandboxManager } from '@anthropic-ai/sandbox-runtime'
// Violation tracking
export { SandboxViolationStore } from '@anthropic-ai/sandbox-runtime'
// TypeScript types
export type {
SandboxRuntimeConfig,
NetworkConfig,
FilesystemConfig,
IgnoreViolationsConfig,
SandboxAskCallback,
FsReadRestrictionConfig,
FsWriteRestrictionConfig,
NetworkRestrictionConfig,
} from '@anthropic-ai/sandbox-runtime'
Configuration
Settings File Location
By default, the sandbox runtime looks for configuration at ~/.srt-settings.json. You can specify a custom path using the --settings flag:
srt --settings /path/to/srt-settings.json <command>
Complete Configuration Example
{
"network": {
"allowedDomains": [
"github.com",
"*.github.com",
"lfs.github.com",
"api.github.com",
"npmjs.org",
"*.npmjs.org"
],
"deniedDomains": ["malicious.com"],
"allowUnixSockets": ["/var/run/docker.sock"],
"allowLocalBinding": false
},
"filesystem": {
"denyRead": ["~/.ssh"],
"allowWrite": [".", "src/", "test/", "/tmp"],
"denyWrite": [".env", "config/production.json"]
},
"ignoreViolations": {
"*": ["/usr/bin", "/System"],
"git push": ["/usr/bin/nc"],
"npm": ["/private/tmp"]
},
"enableWeakerNestedSandbox": false
}
Configuration Options
Network Configuration
Uses an allow-only pattern - all network access is denied by default.
network.allowedDomains- Array of allowed domains (supports wildcards like*.example.com). Empty array = no network access.network.deniedDomains- Array of denied domains (checked first, takes precedence over allowedDomains)network.allowUnixSockets- Array of Unix socket paths that can be accessed (macOS only)network.allowLocalBinding- Allow binding to local ports (boolean, default: false)
Filesystem Configuration
Uses two different patterns:
Read restrictions (deny-only pattern) - all reads allowed by default:
filesystem.denyRead- Array of paths to deny read access. Empty array = full read access.
Write restrictions (allow-only pattern) - all writes denied by default:
filesystem.allowWrite- Array of paths to allow write access. Empty array = no write access.filesystem.denyWrite- Array of paths to deny write access within allowed paths (takes precedence over allowWrite)
Path Syntax (macOS):
Paths support git-style glob patterns on macOS, similar to .gitignore syntax:
*- Matches any characters except/(e.g.,*.tsmatchesfoo.tsbut notfoo/bar.ts)**- Matches any characters including/(e.g.,src/**/*.tsmatches all.tsfiles insrc/)?- Matches any single character except/(e.g.,file?.txtmatchesfile1.txt)[abc]- Matches any character in the set (e.g.,file[0-9].txtmatchesfile3.txt)
Examples:
"allowWrite": ["src/"]- Allow write to entiresrc/directory"allowWrite": ["src/**/*.ts"]- Allow write to all.tsfiles insrc/and subdirectories"denyRead": ["~/.ssh"]- Deny read to SSH directory"denyWrite": [".env"]- Deny write to.envfile (even if current directory is allowed)
Path Syntax (Linux):
Linux currently does not support glob matching. Use literal paths only:
"allowWrite": ["src/"]- Allow write tosrc/directory"denyRead": ["/home/user/.ssh"]- Deny read to SSH directory
All platforms:
- Paths can be absolute (e.g.,
/home/user/.ssh) or relative to the current working directory (e.g.,./src) ~expands to the user's home directory
Other Configuration
ignoreViolations- Object mapping command patterns to arrays of paths where violations should be ignoredenableWeakerNestedSandbox- Enable weaker sandbox mode for Docker environments (boolean, default: false)
Common Configuration Recipes
Allow GitHub access (all necessary endpoints):
{
"network": {
"allowedDomains": [
"github.com",
"*.github.com",
"lfs.github.com",
"api.github.com"
],
"deniedDomains": []
},
"filesystem": {
"denyRead": [],
"allowWrite": ["."],
"denyWrite": []
}
}
Restrict to specific directories:
{
"network": {
"allowedDomains": [],
"deniedDomains": []
},
"filesystem": {
"denyRead": ["~/.ssh"],
"allowWrite": [".", "src/", "test/"],
"denyWrite": [".env", "secrets/"]
}
}
Common Issues and Tips
Running Jest: Use --no-watchman flag to avoid sandbox violations:
srt "jest --no-watchman"
Watchman accesses files outside the sandbox boundaries, which will trigger permission errors. Disabling it allows Jest to run with the built-in file watcher instead.
Platform Support
- macOS: Uses
sandbox-execwith custom profiles (no additional dependencies) - Linux: Uses
bubblewrap(bwrap) for containerization - Windows: Not yet supported
Platform-Specific Dependencies
Linux requires:
bubblewrap- Container runtime- Ubuntu/Debian:
apt-get install bubblewrap - Fedora:
dnf install bubblewrap - Arch:
pacman -S bubblewrap
- Ubuntu/Debian:
socat- Socket relay for proxy bridging- Ubuntu/Debian:
apt-get install socat - Fedora:
dnf install socat - Arch:
pacman -S socat
- Ubuntu/Debian:
ripgrep- Fast search tool for deny path detection- Ubuntu/Debian:
apt-get install ripgrep - Fedora:
dnf install ripgrep - Arch:
pacman -S ripgrep
- Ubuntu/Debian:
Optional Linux dependencies (for seccomp fallback):
The package includes pre-generated seccomp BPF filters for x86-64 and arm architectures. These dependencies are only needed if you are on a different architecture where pre-generated filters are not available:
gccorclang- C compilerlibseccomp-dev- Seccomp library development files- Ubuntu/Debian:
apt-get install gcc libseccomp-dev - Fedora:
dnf install gcc libseccomp-devel - Arch:
pacman -S gcc libseccomp
- Ubuntu/Debian:
macOS requires:
ripgrep- Fast search tool for deny path detection- Install via Homebrew:
brew install ripgrep - Or download from: https://github.com/BurntSushi/ripgrep/releases
- Install via Homebrew:
Development
# Install dependencies
npm install
# Build the project
npm run build
# Build seccomp binaries (requires Docker)
npm run build:seccomp
# Run tests
npm test
# Run integration tests
npm run test:integration
# Type checking
npm run typecheck
# Lint code
npm run lint
# Format code
npm run format
Building Seccomp Binaries
The pre-generated BPF filters are included in the repository, but you can rebuild them if needed:
npm run build:seccomp
This script uses Docker to cross-compile seccomp binaries for multiple architectures:
- x64 (x86-64)
- arm64 (aarch64)
The script builds static generator binaries, generates the BPF filters (~104 bytes each), and stores them in vendor/seccomp/x64/ and vendor/seccomp/arm64/. The generator binaries are removed to keep the package size small.
Implementation Details
Network Isolation Architecture
The sandbox runs HTTP and SOCKS5 proxy servers on the host machine that filter all network requests based on permission rules:
- HTTP/HTTPS Traffic: An HTTP proxy server intercepts requests and validates them against allowed/denied domains
- Other Network Traffic: A SOCKS5 proxy handles all other TCP connections (SSH, database connections, etc.)
- Permission Enforcement: The proxies enforce the
permissionsrules from your configuration
Platform-specific proxy communication:
Linux: Requests are routed via the filesystem over Unix domain sockets (using
socatfor bridging). The network namespace is removed from the bubblewrap container, ensuring all network traffic must go through the proxies.macOS: The Seatbelt profile allows communication only to specific localhost ports where the proxies listen. All other network access is blocked.
Filesystem Isolation
Filesystem restrictions are enforced at the OS level:
- macOS: Uses
sandbox-execwith dynamically generated Seatbelt profiles that specify allowed read/write paths - Linux: Uses
bubblewrapwith bind mounts, marking directories as read-only or read-write based on configuration
Default filesystem permissions:
Read (deny-only): Allowed everywhere by default. You can deny specific paths.
- Example:
denyRead: ["~/.ssh"]to block access to SSH keys - Empty
denyRead: []= full read access (nothing denied)
- Example:
Write (allow-only): Denied everywhere by default. You must explicitly allow paths.
- Example:
allowWrite: [".", "/tmp"]to allow writes to current directory and /tmp - Empty
allowWrite: []= no write access (nothing allowed) denyWritecreates exceptions within allowed paths
- Example:
This model lets you start with broad read access but maximally restricted write access, then explicitly open the holes you need.
Mandatory Deny Paths (Auto-Protected Files)
Certain sensitive files and directories are always blocked from writes, even if they fall within an allowed write path. This provides defense-in-depth against sandbox escapes and configuration tampering.
Always-blocked files:
- Shell config files:
.bashrc,.bash_profile,.zshrc,.zprofile,.profile - Git config files:
.gitconfig,.gitmodules - Other sensitive files:
.ripgreprc,.mcp.json
Always-blocked directories:
- IDE directories:
.vscode/,.idea/ - Claude config directories:
.claude/commands/,.claude/agents/ - Git hooks and config:
.git/hooks/,.git/config
These paths are blocked automatically - you don't need to add them to denyWrite. For example, even with allowWrite: ["."], writing to .bashrc or .git/hooks/pre-commit will fail:
$ srt 'echo "malicious" >> .bashrc'
/bin/bash: .bashrc: Operation not permitted
$ srt 'echo "bad" > .git/hooks/pre-commit'
/bin/bash: .git/hooks/pre-commit: Operation not permitted
Note (Linux): On Linux, mandatory deny paths only block files that already exist. Non-existent files in these patterns cannot be blocked by bubblewrap's bind-mount approach. macOS uses glob patterns which block both existing and new files.
Linux search depth: On Linux, the sandbox uses ripgrep to scan for dangerous files in subdirectories within allowed write paths. By default, it searches up to 3 levels deep for performance. You can configure this with mandatoryDenySearchDepth:
{
"mandatoryDenySearchDepth": 5,
"filesystem": {
"allowWrite": ["."]
}
}
- Default:
3(searches up to 3 levels deep) - Range:
1to10 - Higher values provide more protection but slower performance
- Files in CWD (depth 0) are always protected regardless of this setting
Unix Socket Restrictions (Linux)
On Linux, the sandbox uses seccomp BPF (Berkeley Packet Filter) to block Unix domain socket creation at the syscall level. This provides an additional layer of security to prevent processes from creating new Unix domain sockets for local IPC (unless explicitly allowed).
How it works:
Pre-generated BPF filters: The package includes pre-compiled BPF filters for different architectures (x64, ARM64). These are ~104 bytes each and stored in
vendor/seccomp/. The filters are architecture-specific but libc-independent, so they work with both glibc and musl.Runtime detection: The sandbox automatically detects your system's architecture and loads the appropriate pre-generated BPF filter.
Syscall filtering: The BPF filter intercepts the
socket()syscall and blocks creation ofAF_UNIXsockets by returningEPERM. This prevents sandboxed code from creating new Unix domain sockets.Two-stage application using apply-seccomp binary:
- Outer bwrap creates the sandbox with filesystem, network, and PID namespace restrictions
- Network bridging processes (socat) start inside the sandbox (need Unix sockets)
- apply-seccomp binary applies the seccomp filter via
prctl() - apply-seccomp execs the user command with seccomp active
- User command runs with all sandbox restrictions plus Unix socket creation blocking
Security limitations: The filter only blocks socket(AF_UNIX, ...) syscalls. It does not prevent operations on Unix socket file descriptors inherited from parent processes or passed via SCM_RIGHTS. For most sandboxing scenarios, blocking socket creation is sufficient to prevent unauthorized IPC.
Zero runtime dependencies: Pre-built static apply-seccomp binaries and pre-generated BPF filters are included for x64 and arm64 architectures. No compilation tools or external dependencies required at runtime.
Architecture support: x64 and arm64 are fully supported with pre-built binaries. Other architectures are not currently supported. To use sandboxing without Unix socket blocking on unsupported architectures, set allowAllUnixSockets: true in your configuration.
Violation Detection and Monitoring
When a sandboxed process attempts to access a restricted resource:
- Blocks the operation at the OS level (returns
EPERMerror) - Logs the violation (platform-specific mechanisms)
- Notifies the user (in Claude Code, this triggers a permission prompt)
macOS: The sandbox runtime taps into macOS's system sandbox violation log store. This provides real-time notifications with detailed information about what was attempted and why it was blocked. This is the same mechanism Claude Code uses for violation detection.
# View sandbox violations in real-time
log stream --predicate 'process == "sandbox-exec"' --style syslog
Linux: Bubblewrap doesn't provide built-in violation reporting. Use strace to trace system calls and identify blocked operations:
# Trace all denied operations
strace -f srt <your-command> 2>&1 | grep EPERM
# Trace specific file operations
strace -f -e trace=open,openat,stat,access srt <your-command> 2>&1 | grep EPERM
# Trace network operations
strace -f -e trace=network srt <your-command> 2>&1 | grep EPERM
Advanced: Bring Your Own Proxy
For more sophisticated network filtering, you can configure the sandbox to use your own proxy instead of the built-in ones. This enables:
- Traffic inspection: Use tools like mitmproxy to inspect and modify traffic
- Custom filtering logic: Implement complex rules beyond simple domain allowlists
- Audit logging: Log all network requests for compliance or debugging
Example with mitmproxy:
# Start mitmproxy with custom filtering script
mitmproxy -s custom_filter.py --listen-port 8888
Note: Custom proxy configuration is not yet supported in the new configuration format. This feature will be added in a future release.
Important security consideration: Even with domain allowlists, exfiltration vectors may exist. For example, allowing github.com lets a process push to any repository. With a custom MITM proxy and proper certificate setup, you can inspect and filter specific API calls to prevent this.
Security Limitations
- Network Sandboxing Limitations: The network filtering system operates by restricting the domains that processes are allowed to connect to. It does not otherwise inspect the traffic passing through the proxy and users are responsible for ensuring they only allow trusted domains in their policy.
- Privilege Escalation via Unix Sockets: The
allowUnixSocketsconfiguration can inadvertently grant access to powerful system services that could lead to sandbox bypasses. For example, if it is used to allow access to/var/run/docker.sockthis would effectively grant access to the host system through exploiting the docker socket. Users are encouraged to carefully consider any unix sockets that they allow through the sandbox. - Filesystem Permission Escalation: Overly broad filesystem write permissions can enable privilege escalation attacks. Allowing writes to directories containing executables in
$PATH, system configuration directories, or user shell configuration files (.bashrc,.zshrc) can lead to code execution in different security contexts when other users or system processes access these files. - Linux Sandbox Strength: The Linux implementation provides strong filesystem and network isolation but includes an
enableWeakerNestedSandboxmode that enables it to work inside of Docker environments without privileged namespaces. This option considerably weakens security and should only be used incases where additional isolation is otherwise enforced.
Known Limitations and Future Work
Linux proxy bypass: Currently uses environment variables (HTTP_PROXY, HTTPS_PROXY, ALL_PROXY) to direct traffic through proxies. This works for most applications but may be ignored by programs that don't respect these variables, leading to them being unable to connect to the internet.
Future improvements:
Proxychains support: Add support for
proxychainswithLD_PRELOADon Linux to intercept network calls at a lower level, making bypass more difficultLinux violation monitoring: Implement automatic
strace-based violation detection for Linux, integrated with the violation store. Currently, Linux users must manually runstraceto see violations, unlike macOS which has automatic violation monitoring via the system log store