
promptfoo
Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and…
adversarial-attackai-securitydevsecops+5
24.8k

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and…

Security Scanner for Agent Skills

Automated security analysis pipeline that runs CodeQL queries on GitHub repositories and uses LLMs to classify and filter true vulnerabilities from…

A benchmark for evaluating AI agents on fixing real-world security vulnerabilities.

LLM powered fuzzing via OSS-Fuzz.

AI Code Security — four agents that catch what SAST misses in AI-generated code. Built on GitLab Duo Agent Platform.

Protection against Model Serialization Attacks