GPTFuzz logo

GPTFuzz

sherdencooper/GPTFuzz

Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

GraphCanon updated 2w · GitHub synced 2w · 25 views this month

604 stars87 forksLast push 5mo Python MIT

Decision brief

GPTFuzz leverages auto-generated jailbreak prompts to red team large language models for testing and evaluation.

Good fit when

  • When you need to test the robustness of LLMs against potential manipulative input designed to bypass content controls.
  • To enhance security measures by simulating attacks on AI systems, particularly useful in environments requiring strict regulatory compliance.

Avoid when

  • If your project requires straightforward, uncontroversial testing tools that do not engage with sensitive content control evasion techniques.
  • For general-purpose debugging and optimization tasks where red teaming tactics are not necessary or appropriate.

Observed Jul 17, 2026 · Source: enrich:decision_facts

Verify the decision

Maintenance and security

Full trust report
Maintenance
Slowing (158d since push)
As of 2w
Provenance
Not a fork · Personal account
As of 2w
Security (OSV)
No lockfile
As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install GPTFuzz
PyPI

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Official repo for GPTFUZZER, which focuses on red teaming large language models via auto-generated jailbreak prompts.

Capability facts

Languages
python

Source: github.language · Aug 5, 2026

Categories

Tags

README

Installation

Please refer to install.ipynb

For agents

This page has a .md twin and JSON over the API.

Was this helpful?

Anonymous feedback helps us improve pages and translations.