Skip to main content

🥀 Briar — Autonomous AI Pentester (READ ME OUTDATED) My lazy ass is too lazy to update it

Find vulnerabilities before hackers do. Free. Open Source. No Docker.

PyPI Python License Stars

Briar Logo

Briar is an autonomous AI pentester. It scans web applications, injects real payloads, validates exploits, and generates professional security reports — powered by 11 AI providers including a completely free local mode via Ollama.

pip install briar-pentest && briar setup && briar scan -u https://target.com --deep

What Briar Found — Real Example

Against a file server on port 666 (ransomware-like deployment):

# Vulnerability Severity CVSS
1 Path Traversal 🔴 Critical 9.1
2 IDOR — File Enumeration 🟠 High 7.5
3 Unauthenticated File Access 🔴 Critical 9.1
4 Arbitrary File Upload (RCE) 🔴 Critical 9.8
5 Directory Listing 🟠 High 6.5
6 HTTP Verb Tampering 🟡 Medium 5.0
7 Missing Security Headers 🟢 Low 3.1
8 SSRF via URL param 🟠 High 8.6
9 Reflected XSS 🟠 High 7.2
10 Sensitive File Exposure 🟡 Medium 5.3

Each finding includes: copy-paste curl PoC, CVSS score, tech-specific remediation (nginx/Apache/Flask/Express code).


Features

Category Details
🤖 11 AI Providers Ollama (free, local), OpenAI, Claude, DeepSeek, Groq, Mistral, xAI/Grok, Google/Gemini, OpenRouter, Together, Custom
🛡️ 12 Security Agents Recon, Injection, XSS, SSRF, Auth, AuthZ, CSRF, Upload, Traversal, RCE, API, Secrets
🎯 No Exploit, No Report Every High/Critical finding replayed and confirmed before reporting
🔌 Blackbox + Whitebox Works with just a URL. Add -r /path/to/source for code-aware analysis
📡 Port Scanning 24 common ports scanned during recon
📓 LLM-Wiki (Obsidian) Interlinked vault, frontmatter YAML, index, log, canvas mindmap — Karpathy pattern
📄 Reports Markdown, Word (.docx), Excel (.xlsx), HTML slides
📊 Charts Donut severity, heatmap severity×endpoint, bar charts (type + agent)
🌐 Dashboard Web UI on port 8233 (FastAPI) with live scan launcher
💾 Workspaces Resume interrupted scans, checkpoint after every agent
⚙️ YAML Config Authenticated scanning, login flows, custom rules (avoid/focus paths)
🐳 No Docker Required Native Python. pip install and go. Docker optional.

Quick Start

# Install
pip install briar-pentest

# Configure (pick Ollama for free local AI)
briar setup

# Quick scan
briar scan -u https://target.com --quick

# Deep scan with browser exploits
briar scan -u https://target.com --deep

# With config file (authenticated)
briar scan -c config.yaml

# Resume interrupted scan
briar scan --resume workspace-name

# Web dashboard
briar serve  # → http://localhost:8233

Config File (YAML)

target:
  url: http://localhost:3000
provider: deepseek
mode: deep

authentication:
  login_url: /rest/user/login
  method: json
  credentials:
    email: admin@test.com
    password: admin123

rules:
  avoid:
    - path: /logout
  focus:
    - path: /api
    - path: /rest

Commands

briar             Show banner + version
briar status      Show configured provider + API key
briar setup       Pick AI provider (interactive)
briar scan        Run pentest (-u URL, --quick, --deep, -c config.yaml)
briar serve       Start web dashboard (:8233)
briar workspaces  List saved workspaces
briar resume      Resume an interrupted scan

Install from Source

git clone https://github.com/Stiimy/briar
cd briar
pip install -e .
briar setup

License: AGPL-3.0 — Free. Forever.

"No exploit, no report."

Metadata

Release files for briar-pentest 0.4.62

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for briar-pentest 0.4.62
File Size Uploaded Provenance
briar_pentest-0.4.62.tar.gz 113.2 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for briar-pentest 0.4.62
File Interpreter ABI Platform
briar_pentest-0.4.62-py3-none-any.whl Python 3 none any Details

Total release size: 260.7 kB

Release files / briar_pentest-0.4.62.tar.gz

Download URL briar_pentest-0.4.62.tar.gz
Size 113.2 kB
Tags Source
SHA-256 checksum
How to use checksums
b75e09acf8ab369336987e19f3d101a5fc01ead53456eb376425068ee4180331
BLAKE2b-256 checksum
How to use checksums
ef5d476355d49a458380f70edb9df6c2b94c432d4c86bf1a5604cee00c6f5674
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.14.6

Release files / briar_pentest-0.4.62-py3-none-any.whl

Download URL briar_pentest-0.4.62-py3-none-any.whl
Size 147.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
a35c1360bc6c55c1b71c41d796a719b7afce94b6ad5b1d4975654029fa715fdc
BLAKE2b-256 checksum
How to use checksums
4bf28d026f8748a87bca64284ca0a179fbef4aef32de12f7852f32afcff9994a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.14.6

Security for briar-pentest 0.4.62

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

Release history Release notifications | RSS feed

This release

0.4.62 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page