oss-fuzz-gen and ps-fuzz

These are complements: OSS-Fuzz-Gen uses LLMs to generate fuzzing test cases for finding vulnerabilities in open-source software, while PS-Fuzz uses fuzzing techniques to test the robustness of LLM system prompts themselves—addressing security from opposite directions in the AI+security stack.

oss-fuzz-gen
59
Established
ps-fuzz
56
Established
Maintenance 10/25
Adoption 10/25
Maturity 16/25
Community 23/25
Maintenance 10/25
Adoption 10/25
Maturity 16/25
Community 20/25
Stars: 1,372
Forks: 208
Downloads:
Commits (30d): 0
Language: Python
License: Apache-2.0
Stars: 642
Forks: 88
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No Package No Dependents

About oss-fuzz-gen

google/oss-fuzz-gen

LLM powered fuzzing via OSS-Fuzz.

This framework helps software security teams automate and enhance their fuzz testing efforts by using Large Language Models (LLMs) to generate new fuzz targets for C, C++, Java, and Python projects. It takes existing project code and an LLM as input, then outputs new fuzzing code and detailed reports on its effectiveness, including crash discovery and code coverage. This is intended for security engineers and quality assurance professionals focused on identifying vulnerabilities in open-source and proprietary software.

software-security vulnerability-research fuzz-testing static-analysis quality-assurance

About ps-fuzz

prompt-security/ps-fuzz

Make your GenAI Apps Safe & Secure :rocket: Test & harden your system prompt

This tool helps you evaluate and improve the security of your GenAI application's core instructions, known as the system prompt. It takes your system prompt as input and runs various simulated attacks to identify vulnerabilities, giving you a security evaluation. The person building or managing a GenAI application, concerned about misuse or security breaches, would use this to harden their system.

GenAI Security Prompt Engineering Application Hardening AI Risk Management LLM Safety

Scores updated daily from GitHub, PyPI, and npm data. How scores work