prompt-injection-defense

SkillAI & models

Defend the agent against adversarial Unicode it obeys but a human can't see: bidi/Trojan Source, tag-char smuggling, zero-width text, homoglyphs. Triggers on: prompt injection, scan for hidden unicode, hidden characters, zero-width space, Trojan Source, ASCII smuggling, poisoned CLAUDE.md, MCP tool

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the prompt-injection-defense skill

Signals

GitHub stars
36
Forks
5
Last commit
Aug 2026
Advanced
Catalog kind
skill
Gateway key
prompt-injection-defense
Source
github.com/0xdarkmatter/claude-mods