SoftwareBenchmark
Open-Prompt-Injection
byAthena
Benchmark for prompt injection attacks and defenses in LLMs
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, an extended version of a presentation given at the Safer with Google Summit 2025.
