Is e2b safe?
What e2b does
e2b is the JavaScript and TypeScript SDK for E2B, which runs AI-generated code in isolated sandboxes in the cloud. The npm author field lists FoundryLabs, Inc., and the code lives in e2b-dev/e2b under the MIT license; it needs Node.js 22.19 or later. With an E2B_API_KEY from an E2B account, your code creates sandboxes, runs commands in them and manages volumes, templates and secrets through the E2B API, and the separate @e2b/code-interpreter package adds runCode(). The code and commands run on E2B's servers, not on your machine. Before installing, keep the API key in an environment variable or secret store, and give sandboxes only the credentials a task needs.
- Node.js filesystem read
- Node.js filesystem write/delete
- Node.js network egress
What to do: Nothing here argues against installing it. Grant the capabilities it lists only if you expect the tool to need them.
e2b is an npm package analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators. It can: filesystem read, filesystem write and network egress — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).
e2b 2.64.0
Get notified when this component changes
Change alerts aren't live yet. Leave your email and we'll let you know when they launch. We use it only for this and delete it on request.
Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of e2b's authors. Report a false positive.
Behavioral traits
How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.
Findings (3)
The component reads files from disk.
return node_fs.default.readFileSync(dockerignorePath, "utf-8").replace(/^\uFEFF/, "").split("\n").filter((line) => !line.startsWith("#")).map((line) => line.trim()).filter((line) => line);if (typeof pathOrContent === "string") return node_fs.default.readFileSync(node_path.default.join(contextPath, pathOrContent), "utf-8");
body: node_stream.default.Readable.toWeb(node_fs.default.createReadStream(filePath)),
if (node_fs.default.existsSync(dockerfileContentOrPath) && node_fs.default.statSync(dockerfileContentOrPath).isFile()) return node_fs.default.readFileSync(dockerfileContentOrPath, "utf-8");
return fs.readFileSync(dockerignorePath, "utf-8").replace(/^\uFEFF/, "").split("\n").filter((line) => !line.startsWith("#")).map((line) => line.trim()).filter((line) => line);if (typeof pathOrContent === "string") return fs.readFileSync(path.join(contextPath, pathOrContent), "utf-8");
body: stream.Readable.toWeb(fs.createReadStream(filePath)),
if (fs.existsSync(dockerfileContentOrPath) && fs.statSync(dockerfileContentOrPath).isFile()) return fs.readFileSync(dockerfileContentOrPath, "utf-8");
Why it matters: Usually legitimate, but worth confirming it can't be steered into reading sensitive files.
Fix: Confirm which files are read and that paths cannot be influenced by untrusted input to reach sensitive locations.
The component writes or deletes files on disk.
const cleanup = () => node_fs.default.promises.rm(tmpDir, {const cleanup = () => fs.promises.rm(tmpDir, {Why it matters: Usually legitimate, but worth confirming the paths can't be controlled by untrusted input.
Fix: Confirm which files are written/deleted and that paths cannot be influenced by untrusted input.
The component makes outbound network requests.
return ((input, init) => globalThis.fetch(input, init));
const response = await fetch(request.url, {return ((input, init) => globalThis.fetch(input, init));
const response = await fetch(request.url, {Why it matters: Usually legitimate, but confirm the destinations are expected and no sensitive data leaves.
Fix: Confirm the destination hosts are expected and that no sensitive data is sent off-host.
Maintain e2b?
The free Claude Code plugin scans each npm, PyPI or MCP package with this report's open-source engine before the install command runs. It runs on your machine and needs no account.
Check your own component
Run the same evidence-backed scan on any MCP server, agent skill, or package.
Scan your own componentHow we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →