Skip to content
ai-supply.store
DiscoverCategoriesLeaderboardsCommunityAgent APIFAQ
Sign inSign up free
catalog / Agentic capability / E2B Code Interpreter SDK
◆SkillAgentic capabilityFree

E2B Code Interpreter SDK

Secure cloud sandboxes for running AI-generated code — spin up a Python/JS interpreter in 150ms from your agent.

@ai-supply
Installs221k
⟳ upstream @e2b/cli@2.15.1 · updated 3d ago
↗ Source repository
← More Agentic capabilityAgentic capability leaderboard →How we grade security →Source ↗
! Grade B · 88/100 · ReviewSecurity assessment
✓No compromise signals26capabilities surfaced1known CVE7of 20 OWASP controls clear
Broad capability surfacePotentially unbounded loopSuspicious network referencesBroad capability surface
scanned 1d ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

E2B Code Interpreter SDK

The E2B SDK provides secure, isolated cloud micro-VMs that let AI agents safely execute code generated by LLMs. Each sandbox starts in ~150ms and can run arbitrary Python, JavaScript, shell commands, and Jupyter-style notebooks — without any risk to the host system.

Key Features

  • Sub-200ms cold start: VMs are pre-warmed; your agent never waits long for a sandbox
  • Persistent state: variables, files, and installed packages persist for the lifetime of the sandbox session
  • Code interpreter: Jupyter-compatible kernel with stdout, stderr, rich display (plots, DataFrames, HTML)
  • File system: upload/download files, mount datasets, and share artifacts back to the user
  • Custom images: bake in your own dependencies with a one-line template definition
  • Multi-language: Python, Node.js, Java, Go, Rust — any language installable in a Debian container

Quick Start

pip install e2b-code-interpreter
from e2b_code_interpreter import Sandbox

with Sandbox() as sbx:
    execution = sbx.run_code("""
import pandas as pd
import matplotlib.pyplot as plt

df = pd.DataFrame({'x': range(10), 'y': [i**2 for i in range(10)]})
df.plot(x='x', y='y')
plt.savefig('chart.png')
print('Chart saved!')
""")
    print(execution.text)
    sbx.files.download('chart.png', 'local_chart.png')
npx ai-supply add e2b-code-interpreter-sdk

Curated mirror of the open-source E2B SDK (Apache-2.0). Get it from the source.

Rating rank
#1
of 35 in Agentic capability
Install rank
#9
of 35 in Agentic capability
Security score
88/100 · B
review
Security rank
#13
of 35 in Agentic capability
Installs
221k
cat avg 186k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Agentic capability leaderboard →
! Security: Review · 8888/100 · grade Bscanned 1d ago
✓ no compromise signals27 risk-surface · 8/20 OWASP controls flagged

Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.

What this capability can do · med confidence (static)
⚑ filesystem⚑ shell⚑ network⚑ secrets
egress → unpkg.com, e2b.dev, discord.gg, registry.npmjs.org, pypi.org, go.microsoft.com, static.pepy.tech, www.npmjs.com +32
skill: stripe-projects30 scripts

Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).

OWASP Top 10 for LLM Applications
⚠LLM02Sensitive Information Disclosurehigh
Secrets, credentials or PII shipped inside the artifact.
•Embedded credentials — found: hardcoded credential · e2b-dev-E2B-b511953/packages/js-sdk/tests/sandbox/secure.test.ts (CWE-798)expected
⚠LLM03Supply Chainhigh
Vulnerable/compromised dependencies, models or archives in the artifact.
•Dependency manifest — 3 npm dependencies declared · e2b-dev-E2B-b511953/package.jsonrisk surface
•Dependency manifest — 28 npm dependencies declared · e2b-dev-E2B-b511953/packages/cli/package.jsonrisk surface
•Dependency manifest — 1 npm dependencies declared · e2b-dev-E2B-b511953/packages/cli/testground/demo-basic/package.jsonrisk surface
•Dependency manifest — 37 npm dependencies declared · e2b-dev-E2B-b511953/packages/js-sdk/package.jsonrisk surface
•Vulnerable dependencies — 3 known vulnerabilities in: brace-expansion@1.1.16, brace-expansion@2.1.2, brace-expansion@5.0.7 (CWE-1395)known CVE · -12 pts
⚠LLM05Improper Output Handlinghigh
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — dynamic code execution · e2b-dev-E2B-b511953/.changeset/olive-pugs-refuse.md (CWE-95)expected
•Suspicious code patterns — destructive rm -rf / · e2b-dev-E2B-b511953/copybara.Dockerfile (CWE-78)expected
•Suspicious code patterns — child_process exec · e2b-dev-E2B-b511953/packages/cli/src/utils/openBrowser.ts (CWE-78)expected
•Suspicious code patterns — environment/secret exfiltration · e2b-dev-E2B-b511953/packages/js-sdk/tests/runtimes/cloudflare-deploy/run.test.ts (CWE-200)expected
⚠LLM06Excessive Agencyhigh
Over-broad tool/permission surface or unrestricted egress.
•External endpoints declared — 1 distinct host(s) · e2b-dev-E2B-b511953/.changeset/config.jsonexpected
•External endpoints declared — 2 distinct host(s) · e2b-dev-E2B-b511953/.github/ISSUE_TEMPLATE/config.ymlexpected
•External endpoints declared — 9 distinct host(s) · e2b-dev-E2B-b511953/.gitignoreexpected
•External endpoints declared — 6 distinct host(s) · e2b-dev-E2B-b511953/README.mdexpected
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · e2b-dev-E2B-b511953/copy.bara.sky (CWE-272)risk surface
•External endpoints declared — 7 distinct host(s) · e2b-dev-E2B-b511953/packages/js-sdk/README.mdexpected
•Egress to a private/loopback host — 127.0.0.1 · e2b-dev-E2B-b511953/packages/js-sdk/src/connectionConfig.ts (CWE-918)expected
•Broad capability surface — 4 high-impact capability categories referenced — verify least-privilege · e2b-dev-E2B-b511953/packages/js-sdk/src/envd/schema.gen.ts (CWE-272)risk surface
•External endpoints declared — 3 distinct host(s) · e2b-dev-E2B-b511953/packages/js-sdk/src/sandbox/index.tsexpected
•External endpoints declared — 4 distinct host(s) · e2b-dev-E2B-b511953/packages/js-sdk/src/volume/client.tsexpected
⚠LLM07System Prompt Leakagehigh
Secrets, internal hosts or proprietary logic exposed in shipped prompts.
•Internal host / private infrastructure reference — shipped content references a private IP range or internal-only host · e2b-dev-E2B-b511953/packages/js-sdk/src/sandbox/mcp.d.ts (CWE-200)risk surface
•Embedded credentials — found: hardcoded credential · e2b-dev-E2B-b511953/packages/js-sdk/tests/sandbox/secure.test.ts (CWE-798)expected
⚠LLM10Unbounded Consumptionmedium
Unbounded loops/recursion causing DoS or runaway cost.
Enforced at runtime by the gateway (rate limits + spend caps + size caps); static check flags unbounded loops.
•Potentially unbounded loop — an infinite loop (while True / while(1) / for(;;)) may cause runaway consumption · e2b-dev-E2B-b511953/packages/cli/src/commands/sandbox/utils.ts (CWE-835)risk surface
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
✓LLM01Prompt InjectionPassed
✓LLM04Data and Model PoisoningPassed
Backdoors/poisoning in training data or serialized models.
Behavioral poisoning needs model execution; static check covers unsafe serialization + dataset skew only.
✓LLM08Vector and Embedding WeaknessesPassed
PII or plaintext source leakage in embedding/vector exports.
Embedding inversion/poisoning is largely runtime; static check covers PII in vector exports.
OWASP Machine Learning Security Top 10
⚠ML06AI Supply Chainhigh
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Dependency manifest — 3 npm dependencies declared · e2b-dev-E2B-b511953/package.jsonrisk surface
•Dependency manifest — 28 npm dependencies declared · e2b-dev-E2B-b511953/packages/cli/package.jsonrisk surface
•Dependency manifest — 1 npm dependencies declared · e2b-dev-E2B-b511953/packages/cli/testground/demo-basic/package.jsonrisk surface
•Dependency manifest — 37 npm dependencies declared · e2b-dev-E2B-b511953/packages/js-sdk/package.jsonrisk surface
•Vulnerable dependencies — 3 known vulnerabilities in: brace-expansion@1.1.16, brace-expansion@2.1.2, brace-expansion@5.0.7 (CWE-1395)known CVE · -12 pts
⚠ML09Output Integrityhigh
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — dynamic code execution · e2b-dev-E2B-b511953/.changeset/olive-pugs-refuse.md (CWE-95)expected
•Suspicious code patterns — destructive rm -rf / · e2b-dev-E2B-b511953/copybara.Dockerfile (CWE-78)expected
•Suspicious code patterns — child_process exec · e2b-dev-E2B-b511953/packages/cli/src/utils/openBrowser.ts (CWE-78)expected
•Suspicious code patterns — environment/secret exfiltration · e2b-dev-E2B-b511953/packages/js-sdk/tests/runtimes/cloudflare-deploy/run.test.ts (CWE-200)expected
§ML01Input Manipulation (Adversarial)Governance
Models vulnerable to adversarial perturbations.
Requires runtime robustness evaluation; addressed via publisher robustness attestation.
§ML03Model InversionGovernance
Training data reconstructable from a model's outputs.
Runtime/evaluation property; addressed via model-card data-provenance + DP attestation.
§ML04Membership InferenceGovernance
Determining whether a record was in the training set.
Runtime/evaluation property; addressed via overfitting disclosure + DP attestation.
§ML08Model SkewingGovernance
Models trained on skewed data producing biased output.
Requires fairness evaluation; addressed via model-card bias/limitations disclosure.
✓ML02Data PoisoningPassed
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
✓ML05Model TheftPassed
Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
✓ML07Transfer Learning AttackPassed
Backdoored base models / LoRA adapters propagating to derivatives.
Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.
✓ML10Model Poisoning (Weights)Passed
Tampered model weight files; integrity must be verifiable.
Static check enforces safe formats + records a content hash for downstream verification.
Other findings (28) · hygiene / uncategorized
•Unrecognized file type — '.editorconfig' is not on the allowlist · e2b-dev-E2B-b511953/.editorconfigrisk surface
•Unrecognized file type — '.gitattributes' is not on the allowlist · e2b-dev-E2B-b511953/.gitattributesrisk surface
•Unrecognized file type — '.gitignore' is not on the allowlist · e2b-dev-E2B-b511953/.gitignorerisk surface
•Unrecognized file type — '.npmrc' is not on the allowlist · e2b-dev-E2B-b511953/.npmrcrisk surface
•Unrecognized file type — '.prettierignore' is not on the allowlist · e2b-dev-E2B-b511953/.prettierignorerisk surface
•Unrecognized file type — '.prettierrc' is not on the allowlist · e2b-dev-E2B-b511953/.prettierrcrisk surface
•Unrecognized file type — '.tool-versions' is not on the allowlist · e2b-dev-E2B-b511953/.tool-versionsrisk surface
•Unrecognized file type — '.ini' is not on the allowlist · e2b-dev-E2B-b511953/.vale.inirisk surface
•Unrecognized file type — '.?' is not on the allowlist · e2b-dev-E2B-b511953/CODEOWNERSrisk surface
•Unrecognized file type — '.dockerfile' is not on the allowlist · e2b-dev-E2B-b511953/codegen.Dockerfilerisk surface
•Unrecognized file type — '.sky' is not on the allowlist · e2b-dev-E2B-b511953/copy.bara.skyrisk surface
•Unrecognized file type — '.envrc' is not on the allowlist · e2b-dev-E2B-b511953/packages/cli/.envrcrisk surface
•Unrecognized file type — '.hbs' is not on the allowlist · e2b-dev-E2B-b511953/packages/cli/src/templates/python-build-async.hbsrisk surface
•Unrecognized file type — '.dockerignore' is not on the allowlist · e2b-dev-E2B-b511953/packages/cli/testground/demo-basic/.dockerignorerisk surface
•Unrecognized file type — '.mjs' is not on the allowlist · e2b-dev-E2B-b511953/packages/cli/testground/demo-basic/main.mjsrisk surface
•Suspicious network references — raw IP URL (1 URLs) · e2b-dev-E2B-b511953/packages/cli/tests/attribution.test.tsrisk surface
•Unrecognized file type — '.mts' is not on the allowlist · e2b-dev-E2B-b511953/packages/js-sdk/example.mtsrisk surface
•Suspicious network references — raw IP URL (11 URLs) · e2b-dev-E2B-b511953/packages/js-sdk/tests/api/http2.test.tsrisk surface
•Suspicious network references — raw IP URL (17 URLs) · e2b-dev-E2B-b511953/packages/js-sdk/tests/envd/http2.test.tsrisk surface
•Unrecognized file type — '.jsonc' is not on the allowlist · e2b-dev-E2B-b511953/packages/js-sdk/tests/runtimes/cloudflare-deploy/wrangler.jsoncrisk surface
•Suspicious network references — raw IP URL (18 URLs) · e2b-dev-E2B-b511953/packages/js-sdk/tests/sandbox/network.test.tsrisk surface
•Suspicious network references — raw IP URL (4 URLs) · e2b-dev-E2B-b511953/packages/js-sdk/tests/volume/volume.test.tsrisk surface
•Unrecognized file type — '.typed' is not on the allowlist · e2b-dev-E2B-b511953/packages/python-sdk/e2b/api/client/py.typedrisk surface
•Suspicious network references — raw IP URL (6 URLs) · e2b-dev-E2B-b511953/packages/python-sdk/tests/async/volume_async/test_volume.pyrisk surface
•Suspicious network references — raw IP URL (2 URLs) · e2b-dev-E2B-b511953/packages/python-sdk/tests/envd_frame_server.pyrisk surface
•Suspicious network references — raw IP URL (15 URLs) · e2b-dev-E2B-b511953/packages/python-sdk/tests/test_envd_client_transport.pyrisk surface
•Suspicious network references — raw IP URL (3 URLs) · e2b-dev-E2B-b511953/packages/python-sdk/tests/test_envd_plain_http_errors.pyrisk surface
•Unrecognized file type — '.proto' is not on the allowlist · e2b-dev-E2B-b511953/spec/envd/filesystem/filesystem.protorisk surface
✔ verified source · pinned e2b-dev-E2B-b511953 · changed since last scan · +egress 49983-sandbox-id.e2b.app, api.${domain}${path}
Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/e2b-code-interpreter-sdk/check). Click a policy:

Consume E2B Code Interpreter SDK programmatically. Authenticate with an API key or session — see Authorize an agent.

# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/e2b-code-interpreter-sdk

# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/e2b-code-interpreter-sdk/check \
  -H "Content-Type: application/json" \
  -d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'

# CLI
npx ai-supply add e2b-code-interpreter-sdk

# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/e2b-code-interpreter-sdk/install \
  -H "Authorization: Bearer $AIM_KEY"

# MCP tool
install_listing({ "slug": "e2b-code-interpreter-sdk" })
OpenAPI spec →
vlatest
! Security: Review · 881mo ago

Curated mirror — latest upstream source. See the repository for tagged releases.

Sign in and install this listing to leave a review.

More from @ai-supply

View profile →
◉Agent
MetaGPT
Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.
↓ 1.0M
⇄Connector
vLLM
High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
↓ 892k
⇄Connector
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
↓ 811k
△Eval
Weights & Biases (wandb)
ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.
↓ 784k
ai-supply.store

Free, security-vetted AI capabilities — skills, MCPs, plugins, agents, datasets and more, each graded and freshness-tracked, and built for humans and agents alike.

api · v3.1status · all green
Contact
support@ai-supply.storesecurity@ai-supply.store
Catalog
  • Discover
  • Categories
  • Leaderboards
  • Benchmarks
  • Security
  • Scan a repo
Community
  • Community
  • FAQ
For agents
  • Quickstart (60s)
  • Authorize an agent
  • Agent API
  • OpenAPI spec
For builders
  • Publish
  • Dashboard
Account
  • Create account
  • Sign in
  • Settings
Legal
  • Terms
  • Publisher Agreement
  • Acceptable Use
  • Privacy