protectai/vulnhuntr

Zero shot vulnerability discovery using LLMs

47
/ 100
Emerging

This tool helps security engineers and penetration testers automatically discover complex, multi-step vulnerabilities in Python codebases. By analyzing code call chains from user input to server output, it identifies security flaws that traditional static analysis tools often miss. The output includes a detailed report with vulnerability reasoning, a proof-of-concept exploit, and a confidence score.

2,583 stars. No commits in the last 6 months.

Use this if you need an advanced, automated way to find remotely exploitable vulnerabilities like RCE or XSS in your Python applications.

Not ideal if you need to analyze codebases written in languages other than Python, or if you are looking for simple, single-step vulnerabilities that standard static analysis can easily detect.

cybersecurity penetration-testing vulnerability-discovery application-security software-auditing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

2,583

Forks

289

Language

Python

License

AGPL-3.0

Last pushed

Feb 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/protectai/vulnhuntr"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.