
garak
NVIDIA
Open-source NVIDIA scanner that probes LLMs for jailbreaks, prompt injection, leakage and toxicity.
↑↓ chooseEnter openTab switch area/ or Ctrl K search from any page

by Promptfoo (now part of OpenAI)
Open-source CLI and library to evaluate and red-team LLM apps, agents and RAG systems in CI.
From promptfoo's own website and public documents, updated 4 Nov 2026. Not a hands-on review: I add a verdict only to products I use myself.
Promptfoo is a CLI and library for evaluating and red-teaming LLM-based apps, including prompts, agents and RAG systems. It runs automated evaluations and compares models side by side, among them OpenAI, Anthropic, Azure, Bedrock and Ollama.
Red teaming covers vulnerability scanning and security vulnerability reports. A code scanning feature reviews pull requests for LLM-related security and compliance issues. Configs are declarative and checks can run in CI/CD pipelines. The README says evals run locally, so prompts stay on the user's machine.
The licence is MIT and the repository shows about 26.8k stars. The README states that Promptfoo is now part of OpenAI and that the project remains open source.
Best forDevelopers who want LLM tests and red-team scans inside their CI pipeline
Automated evaluations and side-by-side model comparison.
Vulnerability scanning with security reports.
Reviews pull requests for LLM security and compliance issues.
Declarative configs run in pipelines.
Evals run locally, according to the README.
OpenAI, Anthropic, Azure, Bedrock and Ollama.
From the vendor's own integration list or documentation.
Starting price
Free (open source)
Current prices on the vendor's site · Checked 4 Nov 2026. Prices change often; the vendor's page wins.
No public independent audit found.

NVIDIA
Open-source NVIDIA scanner that probes LLMs for jailbreaks, prompt injection, leakage and toxicity.
Commercial platform for continuous AI red teaming and attack-led security of AI systems and agents.
Agent security platform with AI-SPM, runtime detection and response, access control and red teaming.

Microsoft
Open-source Microsoft AI Red Team toolkit for scanning and attacking generative AI systems.
promptfoo vs garakpromptfoo vs Mindgardpromptfoo vs Noma Security
Open-source CLI and library to evaluate and red-team LLM apps, agents and RAG systems in CI.
promptfoo starts at Free (open source), according to its pricing page (checked 4 Nov 2026).
Yes. promptfoo has a free plan or tier; check the pricing page for its limits.
Products in the same category include garak, Mindgard, Noma Security, PyRIT.
Not yet. This page lists published facts only. When I test it, my verdict will appear at the top.
Spotted something out of date? Tell me through the contact page and I will fix it.
By using this site, you agree to the Privacy Policy.