garak

What it is

An open-source scanner that probes a language model for weaknesses — prompt injection, data leakage, jailbreaks, toxic output — and reports what it found. Free.

Why I recommend it

Point it at a model you are about to rely on and see how it fails before your users do.

Topics

#ai ethics #ai-risk #ai-safety #developer-tools #free #open-source #prompt-injection #red-teaming #research #security #technology-and-ethics #testing

Added Sep 17, 2026 · 0 opens