Agent skill · Audited from source

functions

skill · browserbase/skillsLicence not declaredAudited 29 Oct 2026 · source 45d21dc75974

★ 3,745pushed 1 day ago
!CAUTIONGrade B · 89/100 · 3 findings · 45d21dc
3,745repo stars · whole browserbase/skills

Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit 45d21dc75974 and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 3 findings, 0 critical or high. What it does: Deploy serverless browser automation as cloud functions using Browserbase. Use when the user wants to deploy browser automation to run on a schedule or cron, create a webhook endpoint for browser tasks, run automation…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “functions (browserbase/skills)”. Retrieved 29 Oct 2026. https://modelsatlas.com/skills/browserbase/functions

Trust audit

Audit 0.4.1 · source read 29 Oct 2026

Trust score89/100!CAUTION B
0 critical0 high2 medium0 low1 info

CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA2
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS1
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (3)

MEDIUMNetwork egressnet.raw_ip · SKILL.md:84
F-04 Network egressCWE-200 · CWE-319Layer L1
Server runs at `http://127.0.0.1:14113`
Why
No further detail recorded for this rule.
Fix
—
MEDIUMNetwork egressnet.raw_ip · SKILL.md:89
F-04 Network egressCWE-200 · CWE-319Layer L1
curl -X POST http://127.0.0.1:14113/v1/functions/my-function/invoke \
Why
No further detail recorded for this rule.
Fix
—
INFOPrompt injectionprompt.credential_read · REFERENCE.md:128
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
cat .env
Why
asks the agent to read credentials
Fix
—

Audit 0.4.1 · source sha 45d21dc75974 · 29 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherbrowserbase GitHub organizationOwner of the repository this skill is read from
  • Source folderbrowserbase/skills/skills/functionsThe exact folder we audited
  • LicenceNot declaredAs the repository states it
  • Commit pinned for this verdict45d21dc75974A new audit runs when the source changes
  • Repository statusNot archivedLast push 1 day ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Deploy serverless browser automation as cloud functions using Browserbase. Use when the user wants to deploy browser automation to run on a schedule or cron, create a webhook endpoint for browser tasks, run automation…

---
name: functions
description: "Deploy serverless browser automation as cloud functions using Browserbase. Use when the user wants to deploy browser automation to run on a schedule or cron, create a webhook endpoint for browser tasks, run automation in the cloud instead of locally, or asks about Browserbase Functions."
compatibility: "Requires the browse CLI (`npm install -g browse`), Node.js 18+ with pnpm or npm, and BROWSERBASE_API_KEY."
license: MIT
allowed-tools: Bash Read Write Edit
---

# Browserbase Functions

Deploy serverless browser automation using the official `browse` CLI.

## Prerequisites

Get an API key from: https://browserbase.com/settings

```bash
export BROWSERBASE_API_KEY="your_api_key"
```

## Creating a Function Project

### 1. Initialize

```bash
browse functions init my-function
cd my-function
```

This creates:
```
my-function/
├── package.json
├── index.ts        # Your function code
└── .env            # Add credentials here
```

### 2. Add Credentials to .env

```bash
echo "BROWSERBASE_API_KEY=$BROWSERBASE_API_KEY" >> .env
```

### 3. Install Dependencies

```bash
pnpm install
```

## Function Structure

```typescript
import { defineFn } from "@browserbasehq/sdk-functions";
import { chromium } from "playwright-core";

defineFn("my-function", async (context) => {
  const { session, params } = context;

  // Connect to browser
  const browser = await chromium.connectOverCDP(session.connectUrl);
  const page = browser.contexts()[0]!.pages()[0]!;

  // Your automation
  await page.goto(params.url || "https://example.com");
  const title = await page.title();

  // Return JSON-serializable result
  return { success: true, title };
});
```

**Key objects:**
- `context.session.connectUrl` - CDP endpoint to connect Playwright
- `context.params` - Input parameters from invocation

## Development Workflow

### 1. Start Dev Server

```bash
browse functions dev index.ts
```

Server runs at `http://127.0.0.1:14113`

### 2. Test Locally

```bash
curl -X POST http://127.0.0.1:14113/v1/functions/my-function/invoke \
  -H "Content-Type: application/json" \
  -d '{"params": {"url": "https://news.ycombinator.com"}}'
```

### 3. Iterate

The dev server auto-reloads on file changes. Use `console.log()` for debugging - output appears in the terminal.

## Deploying

```bash
browse functions publish index.ts
```

Output:
```
Function published successfully
Build ID: xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx
Function ID: xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx
```

**Save the Function ID** - you need it to invoke.

## Quick Reference

| Command | Description |
|---------|-------------|
| `browse functions init <name>` | Create new project |
| `browse functions dev <file>` | Start local dev server |
| `browse functions publish <file>` | Deploy to Browserbase |

For invocation examples, common patterns, and troubleshooting, see [REFERENCE.md](REFERENCE.md).

Excerpt, first 2,905 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 45d21dc

Download folder ↗
git clone https://github.com/browserbase/skills
git -C skills checkout 45d21dc75974

The author documents no install command, so this uses the repository directly. Our verdict covers commit 45d21dc75974 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. !CAUTION B 89 / 100

    first audit · source 45d21dc75974

README badge

For maintainers · shows the latest audit

ModelsAtlas: CAUTION BMODELSATLASCAUTION · B
[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/browserbase/functions/badge.svg)](https://modelsatlas.com/skills/browserbase/functions/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

Add this badge to your README

[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/browserbase/functions/badge.svg)](https://modelsatlas.com/skills/browserbase/functions/)

Questions about functions

What does the functions skill do?
Browserbase's official collection of agent skills to access the web.
Is functions safe to install?
With care. The audit graded it B (89/100) and found 3 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can functions access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (45d21dc75974), read on 2026-10-29. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.