garak vs PromptRedTeam

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.

PromptRedTeam is an open-source tool that scans user input before it reaches a large language model. It detects direct injection, role manipulation, zero-width injection, delimiter injection, and encoded payloads. Direct-injection checks examine override keywords, conflicting instructions, and prompt structure. Role checks cover known jailbreak patterns, role-play scenarios, and bypass attempts. The tool detects hidden zero-width characters, normalizes Unicode, analyzes Base64 and other encodings, and can decode suspicious text before scanning again. Delimiter checks look for context-breaking markers, Markdown abuse, and structural manipulation. Applications can call the hosted API with a POST request to https://api.promptredteam.com/test, or run PromptRedTeam through self-hosted deployment. The live tester accepts up to 1,000 characters and allows 10 requests per minute; self-hosting provides unlimited usage. Python, JavaScript, and cURL examples are provided. The suggested workflow is to scan incoming text, then block detected threats or log them for review. PromptRedTeam is available through web, API, and self-hosted platforms, with automated detection and hybrid deployment. It is released under the MIT License.