Provides secure, isolated VM environments for executing AI-generated code or system scripts.
Install
mkdir -p .claude/skills/e2b && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13184" && unzip -o skill.zip -d .claude/skills/e2b && rm skill.zipInstalls to .claude/skills/e2b
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Execute AI-generated code in secure isolated E2B cloud sandboxes (SDK v2). Use for running Python/JavaScript/TypeScript/R/Java/Bash code, managing sandbox lifecycle (create, pause, resume, kill, list, connect), running coding agents (Claude Code, Codex, AMP, OpenCode) in sandboxes, git operations inside sandboxes, code contexts for parallel isolated execution, monitoring metrics (CPU, memory, disk), MCP gateway integration (200+ tools), uploading/downloading files, storage bucket mounting (S3, GCS, R2), streaming command output, SSH/PTY access, custom templates with Build System 2.0, and integrating LLMs with code execution capabilities.Key capabilities
- →Execute AI-generated code in isolated cloud sandboxes
- →Manage sandbox lifecycle (create, pause, resume, kill, list, connect)
- →Run Python, JavaScript, TypeScript, R, Java, and Bash code
- →Perform git operations inside sandboxes
- →Upload and download files to/from sandboxes
- →Integrate LLMs with code execution capabilities
How it works
The skill provides an interface to E2B cloud sandboxes, which are isolated VMs for executing AI-generated code. It manages the sandbox lifecycle, allows multi-language code execution, file operations, and git commands, and integrates with LLMs.
Inputs & outputs
When to use e2b
- →Run AI code safely
- →Execute system scripts
- →Isolated environment testing
About e2b
Manages sandbox lifecycles (create, pause, kill) and provides environments for running Python, JS, or Bash safely.
Execute AI-generated code in secure isolated E2B cloud sandboxes (SDK v2). Use for running Python/JavaScript/TypeScript/R/Java/Bash code, managing sandbox lifecycle (create, pause, resume, kill, list, connect), running coding agents (Claude Code, Codex, AMP, OpenCode) in sandboxes, git operations in
When not to use it
- →When a local execution environment is sufficient and isolation is not required
- →When persistent storage beyond the sandbox lifecycle is needed without mounting buckets
- →When the `e2b-code-interpreter` package is not installed for `run_code()` functionality
Prerequisites
Limitations
- →Requires an E2B API key
- →Python `Sandbox()` is a breaking change, use `Sandbox.create()`
- →The `e2b` package does not include `run_code()` (Jupyter-style execution)
How it compares
This skill offers secure, isolated cloud sandboxes for executing AI-generated code with full filesystem, git, and network access, supporting multiple languages and LLM integration, which is more secure and versatile than running code direct
Compared to similar skills
e2b side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| e2b (this skill) | 0 | 7mo | Caution | Intermediate |
| container-security-testing | 1 | 8mo | Review | Intermediate |
| fix-cves | 1 | 7mo | No flags | Intermediate |
| sca-trivy | 1 | 8mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
container-security-testing
Ed1s0nZ
容器安全测试的专业技能和方法论
fix-cves
okteto
Fix all CVEs in the Okteto CLI Docker image by scanning with Trivy and updating vulnerable dependencies and binaries
sca-trivy
rohunj
Software Composition Analysis (SCA) and container vulnerability scanning using Aqua Trivy for identifying CVE vulnerabilities in dependencies, container images, IaC misconfigurations, and license compliance risks. Use when: (1) Scanning container images and filesystems for vulnerabilities and misconfigurations, (2) Analyzing dependencies for known CVEs across multiple languages (Go, Python, Node.js, Java, etc.), (3) Detecting IaC security issues in Terraform, Kubernetes, Dockerfile, (4) Integrating vulnerability scanning into CI/CD pipelines with SARIF output, (5) Generating Software Bill of Materials (SBOM) in CycloneDX or SPDX format, (6) Prioritizing remediation by CVSS score and exploitability.
go-vuln-remediate
infobloxopen
Run Wiz-based vulnerability scan and automatic Go module remediation for containerized Go services in the konk repository. Use when you need to build images, scan CVEs, patch vulnerable dependencies in go.mod/go.sum across konk-service and konk-provision modules, validate builds, and prepare a PR su
run-manual-docker-security-scan
torrust
Guide for running a manual Docker security scan for the tracker runtime image and documenting results. Covers build, Trivy scan, CVE triage, per-CVE catalog updates, and scan history updates. Use when asked to run a manual container scan, triage Docker CVEs, or refresh security scan docs.
gcp-cloud-run
aj-geddes
Deploy containerized applications on Google Cloud Run with automatic scaling, traffic management, and service mesh integration. Use for container-based serverless computing.