agencyenterprise/PromptInject
PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022
ORIGINAL REPOSITORY
agencyenterprise/PromptInject ↗GitHub activity
- Stars
- 528
- Forks
- 59
- Open issues and PRs
- 6
- Repository size
- ~352 KB
- Default branch
- main
- Created
- Oct 25, 2022
- Repository updated
- Oct 30, 2026
- Last push
- Apr 27, 2026
- Language
- Python
- License
- MIT
Topics adversarial-attacks · agi · agi-alignment · ai-alignment · ai-safety · chain-of-thought · gpt-3 · language-models · large-language-models · machine-learning · ml-safety · prompt-engineering
Repository-wide figures from GitHub, checked Nov 3, 2026. Stars are endorsements, not a Mega AI Hub quality rating. Repository size is GitHub’s estimate; a ZIP download may differ.
Resource information
- Original repository
- agencyenterprise/PromptInject
- Credit basis
- GitHub repository owner or organization; individual authorship is not asserted
- Publisher
- agencyenterprise
- Upstream last modified
- Oct 30, 2026
- Official website
- https://github.com/agencyenterprise/PromptInject
- Languages
- Python
- Access
- Open original GitHub repository; publisher terms apply
- Last checked
- Nov 3, 2026
- License
- MIT
- Last record update
- Nov 3, 2026