peaktwilight/nightfang
AI-powered security research automation. Scan LLM endpoints, audit npm packages, review source code. Four autonomous agents discover, attack, verify, and report — every finding proven exploitable. Open source.
Platform-specific configuration:
{
"mcpServers": {
"nightfang": {
"command": "npx",
"args": [
"-y",
"nightfang"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
<p align="center"> </p>
<h1 align="center">Nightfang</h1>
<p align="center"> <strong>Security research automation for the AI era</strong><br/> <em>Scan LLM endpoints. Audit npm packages. Review source code. Prove every finding is real.</em> </p>
<p align="center"> <a href="https://www.npmjs.com/package/nightfang"></a> <a href="https://github.com/peaktwilight/nightfang/blob/main/LICENSE"></a> <a href="https://github.com/peaktwilight/nightfang/actions"></a> <a href="https://github.com/peaktwilight/nightfang/stargazers"></a> <a href="https://github.com/peaktwilight/nightfang/actions/workflows/self-scan.yml"></a> </p>
<p align="center"> </p>
<p align="center"> <a href="#quick-start">Quick Start</a> · <a href="#commands">Commands</a> · <a href="#how-it-works">How It Works</a> · <a href="#what-nightfang-scans">What It Scans</a> · <a href="#how-it-compares">Comparison</a> · <a href="#github-action">CI/CD</a> · <a href="#built-by">About</a> </p>
---
Nightfang is an open-source pentesting toolkit that combines four autonomous AI agents with a template-driven attack engine. Point it at an API, an npm package, or a Git repo — it discovers vulnerabilities, attacks them, re-exploits each finding to eliminate false positives, and generates SARIF reports that p
Loading reviews...