liu00222/Open-Prompt-Injection
Open-Prompt-Injection
This repository provides a benchmark for prompt injection attacks and defenses in LLMs
Builder
liu00222
liu00222 • individual
Stars
450
Using upstream star count
Forks
72
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
Oct 19, 2023
Project creation date
README Summary
This repository is an open-source toolkit for prompt injection attacks and defenses. It enables implementation, evaluation, and extension of attacks, defenses, and LLM-integrated applications and agents. For a deeper dive into prompt injection, see [these slides](https://people.duke.edu/~zg70/code/PromptInjection.pdf), an extended version of a presentation given at the Safer with Google Summit 2025.
Community Evaluation
Loading…AI Dev Skills
Unmapped
Adversarial Machine LearningAI Safety ResearchLarge Language Model SecurityLLM EvaluationNatural Language ProcessingPrompt EngineeringPrompt Injection DetectionRed Team Testing
Tags
Adversarial Machine LearningAI Safety ResearchLarge Language Model SecurityLLM EvaluationNatural Language ProcessingPrompt EngineeringPrompt Injection DetectionRed Team TestingBenchmarkingData ScienceEvalsForkedLarge Language ModelsLoRA / PEFTMistralMusic TechOpenAIPandasPrompt InjectionPythonSecurity
Taxonomy
category
Deployment Context
Industries
Modalities
Skill Areas
tag
Recent Activity
Updated 7 months ago
7 Days
0
30 Days
0
90 Days
0
Quality
research- Quality
- medium
- Maturity
- research
Categories
Evals & BenchmarkingPrimaryDev Tools & AutomationIndustry: Audio & MusicSecurity & SafetyData Science & AnalyticsFoundation ModelsModel TrainingGenerative MediaOther AI / ML
PM Skills
Safety & AlignmentData & Evaluation
Languages
Python100.0%
Timeline
- Project created
- Oct 19, 2023
- Forked
- Mar 21, 2026
- Your last push
- 7 months ago
- Upstream last push
- 7 months ago
- Tracked since
- Oct 29, 2025
Similar Repos
pgvector cosine similarity · $0
Loading…