seojoonkim

seojoonkim/prompt-guard

Skill Claude CodeCodex

600+ pattern AI agent security defense covering prompt injection, supply chain injection, memory poisoning, action gate bypass, unicode steganography, and cascade amplification. Optional API for early-access and premium patterns. Tiered loading, hash cache, 11 SHIELD categories, 10 languages.

seojoonkim/agentlinter

Instructions file

Claude Code instructions for seojoonkim/agentlinter, covering agentlinter project, what is agentlinter?, project structure, your role and context detection.

seojoonkim/agentlinter

Skill Claude CodeCodex

Review a change and report actionable findings.