roost.tools / awesome-safety-tools
Mirror of https://github.com/roostorg/awesome-safety-tools
0
fork

Configure Feed

Select the types of activity you want to include in your feed.

Merge branch 'main' into badwords

authored by

Cassidy James Blaede and committed by
GitHub 5bd4b571 7f6c151a

+2 -2
+2 -2
README.md
··· 69 69 * AI-powered content moderation model to detect harm in text-based interactions 70 70 * [Llama Prompt Guard 2 by Meta](https://github.com/meta-llama/PurpleLlama/blob/main/Llama-Prompt-Guard-2/86M/MODEL_CARD.md) 71 71 * Detects prompt injection and jailbreaking attacks in LLM inputs 72 - * [OpenGuardrails](https://www.openguardrails.com/) 72 + * [OpenGuardrails](https://github.com/openguardrails/openguardrails) 73 73 * Security Gateway providing a transparent reverse proxy for OpenAI apis with integrated safety protection 74 74 * [Purple Llama by Meta](https://github.com/meta-llama/PurpleLlama/tree/main/Llama-Guard3) 75 75 * set of tools to assess and improve LLM security. Includes Llama Guard, CyberSec Eval, and Code Shield ··· 114 114 * Tool for testing prompt injection vulnerabilities in AI systems 115 115 * [Promptfoo](https://github.com/promptfoo/promptfoo) 116 116 * Automated LLM evaluations, report generations, several ready-to-use attack strategies 117 - * [PyRIT Documentation](https://azure.github.io/PyRIT/) 117 + * [PyRIT](https://github.com/Azure/PyRIT) 118 118 * Microsoft’s Python-based tool for AI red teaming and security testing 119 119 * [Socketteer](https://github.com/socketteer?tab=repositories) 120 120 * Allows AI models to interact, helping test conversational weaknesses