garak vs RedFang
garak
garak.aiRedFang
redfang.orgSide by side
| Figure | garak | RedFang |
|---|---|---|
| Price from | Free | $19/mo |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | — |
| Web | — | Yes |
| Windows | Yes | — |
| macOS | Yes | — |
| Linux | Yes | — |
| API | — | Yes |
| Self-hosted | Yes | — |
| Plans published | 1 | 2 |
| Spec score · AI Red Teaming Tools | 7.9 (#9) | 7.5 (#18) |
| Purpose | garak is an LLM vulnerability scanner that probes language models and systems using them for security weaknesses. | RedFang describes itself as an AI red-team scanner for indie builders that scans AI agents, GitHub repositories, and app URLs. |
| Threat coverage | The project lists hallucination, data leakage, prompt injection, misinformation, toxicity generation, and jailbreaks among the weaknesses it probes. | Its seven v1 threat categories include direct prompt injection, tool misuse, sensitive data leakage, output-as-attack-vector, agent overreach, denial-of-wallet, and system-prompt extraction. |
Plans
In their own words
garak
garak is a command-line scanner for probing language models and systems that use them for security weaknesses. Its checks cover issues such as hallucination, data leakage, prompt injection, misinformation, toxicity generation, and jailbreaks. Probes try to elicit failures, while detectors inspect responses for patterns such as unsafe content or a failure to refuse. A standard scan can run without supervision and produce a report, with scan settings available for customization. Integrations include OpenAI, Hugging Face, Cohere, Replicate, AWS Bedrock, LiteLLM, REST-accessible models, and custom Python integrations. Hugging Face models can run locally or be accessed through an inference API or private endpoint. Output includes screen results, a detailed report log, a hit log, and a debug log. garak assesses text output only. It is developed in Linux and OSX and can be installed with pip or from source; listed platforms include Linux, macOS, Windows, and self-hosted use. It is free, with a free plan and no free trial. Listed capabilities include custom metrics, LLM-as-a-judge, and safety evaluations.
RedFang
RedFang is a cloud AI red-team scanner aimed at indie builders. It scans AI agents, GitHub repositories and application URLs, including listed customer-service chatbot targets. Before scanning, it requires a TXT-record or file-upload challenge to verify target ownership. RedFang says scans take five minutes and return grades from A+ to F. Seven v1 categories cover direct prompt injection, tool misuse, sensitive data leakage, output-as-attack-vector, agent overreach, denial-of-wallet and system-prompt extraction. Repository scans look for exposed keys, broken authentication and AI-introduced bugs. The stated methodology follows the OWASP LLM Top 10 threat model and tests 12 known direct prompt-injection patterns per scan. Reports can include plain-language findings, the successful prompt, a curl reproduction command, fix code and a retest. PDF and HTML exports are listed. Free preview costs nothing; Full report costs $19 a month. A shareable badge shows the latest grade, with weekly, daily or continuous scan cadence by tier.