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
PromptInject scores 3.9/10 (Emerging) in Guardrails & Security.
Language Python License MIT Stars 502★ Type library Self-host Yes Repo agencyenterprise/PromptInject Homepage https://github.com/agencyenterprise/PromptInject
Quality
Emerging 3.9
Adoption 18
Activity 17
Maturity 97
Community 20
Capability 50
Show the math
Overall 3.9/10
value = 3.9/10
score = value
Adoption 2.6/10
value = 17.5/100
score = 1 + 9 * value / 100
Activity 2.5/10
value = 17/100
score = 1 + 9 * value / 100
Maturity 9.7/10
value = 96.7/100
score = 1 + 9 * value / 100
Community 2.8/10
value = 20.2/100
score = 1 + 9 * value / 100
Capability 5.5/10
value = 50/100
score = 1 + 9 * value / 100
Key metrics
502★ GitHub stars
0/90d Recent commits
0 devs/90d Recent contributors
3.7y Project age
2mo ago Last commit
Gotchas
No gotchas documented yet. Contribute one if you know a constraint we missed.
Labels
- Self-hosted
Self-hosted
You deploy and operate it yourself; there is no hosted option here.
prompt-injection robustness benchmark adversarial research