✓ Verified 💻 Development ✓ Enhanced Data

Vigil

AI agent safety guardrails for tool calls.

Rating: 4.1 (382 reviews)
Downloads: 23,441 downloads
Version: 1.0.0

Overview

AI agent safety guardrails for tool calls.

Complete Documentation

View Source →

Vigil — Agent Safety Guardrails

Validates what AI agents DO, not what they SAY. Drop-in safety layer for any tool-calling agent.

Prerequisites

This skill requires the vigil-agent-safety npm package (12.3KB, Apache 2.0 license):

bash

npm install vigil-agent-safety

Source code: https://github.com/hexitlabs/vigil
npm: https://www.npmjs.com/package/vigil-agent-safety
The npm package has zero runtime dependencies. This skill is a wrapper that calls that package.

Quick Start

typescript

import { checkAction } from 'vigil-agent-safety';

const result = checkAction({
  agent: 'my-agent',
  tool: 'exec',
  params: { command: 'rm -rf /' },
});

// result.decision === "BLOCK"
// result.reason === "Destructive command pattern"
// result.latencyMs === 0.3

What It Catches

Destructive commands (rm -rf, mkfs, reverse shells) → BLOCK
SSRF (metadata endpoints, localhost, internal IPs) → BLOCK
Data exfiltration (curl to external, .ssh/id_rsa access) → BLOCK
SQL injection (DROP TABLE, UNION SELECT) → BLOCK
Path traversal (../../../etc/shadow) → BLOCK
Prompt injection (ignore instructions, [INST] tags) → BLOCK
Encoding attacks (base64 decode, eval(atob())) → BLOCK
Credential leaks (API keys, AWS keys, tokens) → ESCALATE

22 rules. Zero dependencies. Under 2ms per check.

Modes

typescript

import { configure } from 'vigil-agent-safety';

// warn = log violations but don't block (recommended to start)
configure({ mode: 'warn' });

// enforce = block dangerous calls
configure({ mode: 'enforce' });

// log = silent logging only
configure({ mode: 'log' });

Use with Clawdbot

Add Vigil as a safety layer for your agent tool calls. The scripts/vigil-check.js wrapper lets you validate from the command line:

bash

# Check a tool call
node scripts/vigil-check.js exec '{"command":"rm -rf /"}'
# → BLOCK: Destructive command pattern

# Check a safe call
node scripts/vigil-check.js read '{"path":"./README.md"}'
# → ALLOW

Policies

Load built-in policy templates:

typescript

import { loadPolicy } from 'vigil-agent-safety';

loadPolicy('restrictive');  // Tightest rules
loadPolicy('moderate');     // Balanced (default)
loadPolicy('permissive');   // Minimal blocking

CLI

bash

npx vigil-agent-safety check --tool exec --params '{"command":"ls -la"}'
npx vigil-agent-safety policies

Installation

Terminal bash


openclaw install vigil

Copied!

💻Code Examples

npm install vigil-agent-safety

npm-install-vigil-agent-safety.txt

- **Source code:** https://github.com/hexitlabs/vigil
- **npm:** https://www.npmjs.com/package/vigil-agent-safety
- **The npm package has zero runtime dependencies.** This skill is a wrapper that calls that package.

## Quick Start

// result.latencyMs === 0.3

-resultlatencyms--03.txt

## What It Catches

- Destructive commands (rm -rf, mkfs, reverse shells) → BLOCK
- SSRF (metadata endpoints, localhost, internal IPs) → BLOCK
- Data exfiltration (curl to external, .ssh/id_rsa access) → BLOCK
- SQL injection (DROP TABLE, UNION SELECT) → BLOCK
- Path traversal (../../../etc/shadow) → BLOCK
- Prompt injection (ignore instructions, [INST] tags) → BLOCK
- Encoding attacks (base64 decode, eval(atob())) → BLOCK
- Credential leaks (API keys, AWS keys, tokens) → ESCALATE

22 rules. Zero dependencies. Under 2ms per check.

## Modes

configure({ mode: 'log' });

configure-mode-log-.txt

## Use with Clawdbot

Add Vigil as a safety layer for your agent tool calls. The `scripts/vigil-check.js` wrapper lets you validate from the command line:

# → ALLOW

--allow.txt

## Policies

Load built-in policy templates:

example.ts

import { checkAction } from 'vigil-agent-safety';

const result = checkAction({
  agent: 'my-agent',
  tool: 'exec',
  params: { command: 'rm -rf /' },
});

// result.decision === "BLOCK"
// result.reason === "Destructive command pattern"
// result.latencyMs === 0.3

example.ts

import { configure } from 'vigil-agent-safety';

// warn = log violations but don't block (recommended to start)
configure({ mode: 'warn' });

// enforce = block dangerous calls
configure({ mode: 'enforce' });

// log = silent logging only
configure({ mode: 'log' });

example.sh

# Check a tool call
node scripts/vigil-check.js exec '{"command":"rm -rf /"}'
# → BLOCK: Destructive command pattern

# Check a safe call
node scripts/vigil-check.js read '{"path":"./README.md"}'
# → ALLOW

example.ts

import { loadPolicy } from 'vigil-agent-safety';

loadPolicy('restrictive');  // Tightest rules
loadPolicy('moderate');     // Balanced (default)
loadPolicy('permissive');   // Minimal blocking