prompt-guard

【开发与工程】650+ pattern AI agent security defense covering prompt injection, supply chain injection, memory poisoning, action gate bypass, unicode steganography, cascade amplification, multi-turn manipulation, authority escalation, PII/cloud credentials DLP, and code exfiltration. ClawSecurity-aligned patterns. Optional API for early-access and premium patterns…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准