Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of real attention, adoption, and active maintenance.
This collection provides penetration testers and security researchers with the specific inputs needed to identify system weaknesses. It organizes essential fuzzing payloads for SQL and command injection alongside targeted prompts for testing LLM resistance to adversarial attacks.
By structuring data for bias detection, data leakage, and alignment testing, the repository helps practitioners conduct more systematic authorized security assessments.
WHO IT'S FOR
Penetration testers
conducting authorized vulnerability assessments and fuzzing
AI security researchers
testing LLMs for adversarial prompt resistance
Bug bounty hunters
identifying sensitive data leaks and vulnerabilities
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.