Pattern
NVIDIA Garak
Provide a vulnerability scanner for LLM endpoints, with a catalog of probes that test for specific failure modes (prompt injection, jailbreaks, data leakage, encoding attacks, toxicity, malicious code generation), runnable from the CLI with structured reports.
Classification LLM vulnerability scanner.
Full entry
The complete treatment — problem, how it works, when to use it, sources, and examples — lives in the volume below.
Browse the full pattern index or the catalog.