Adversarial prompt corpus toolkit for LLM/RAG safety: 10 attack categories, 8 Forge mutators, 6 result statuses, CI-ready JSON output.

Go injection benchmark: delivers adversarial prompts through real tool-use paths and scores HIT/MISS per detection signal. Controlled targets only.

A structured NLP dataset for detecting prompt injection attacks, jailbreak attempts, and malicious instruction manipulation in Large Language Models (LLMs). Includes annotated threat categories, risk classifications, and validation-ready samples for AI safety training, security evaluation, and adversarial robustness research.

Systematic red-teaming framework for adversarial prompt evaluation — jailbreak detection, injection classification, attack surface coverage metrics

x402 settlement facilitator + EAS-compatible threat-intel attestation issuer on Base mainnet

Go CLI for AI/LLM infrastructure assessment: hunt, fingerprint, enumerate, passive-recon, and adversarial-corpus generation in one binary.