garak
7,614The LLM vulnerability scanner.
DetectionPost-generationFull HITLStableTier 2BEnvironment
Maturity tier details
Computed tier: 2B(raw score 4.55). Effective tier: 2B.
Facets:documented_in=0evaluated_on=0integration_surfaces=1paper_citations=0recent_commit=2stars=1.55
Source of truth:pipeline/maturity/score.py
Description
NVIDIA garak is an open-source LLM vulnerability scanner: applies a library of probes (jailbreaks, prompt injection, data leakage, malware generation, misinformation) against any LLM endpoint and reports per-probe attack success rates. Models the NVIDIA NeMo Guardrails adversarial test plane.
Why it's included
Canonical LLM-vuln-scanner: complements llm-guard/rebuff by running at assessment time rather than at request time.
Addresses failure modes
- Security vulnerability — Insecure patterns, injection flaws, weak cryptography, secret leakage.
- Fabrication — Generating reference to non-existent APIs, packages, or symbols.
- Scope creep — Actions outside declared task boundary.
Techniques
llm-probesattack-success-rate-metricsdetect-generators