hunt-llm-ai

SkillWeb & browsing

Hunt LLM/AI feature bugs, prompt injection, indirect injection, exfiltration via tool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10). Patterns: direct injection ('ignore previous instructions'), indirect injection via documents/web pages/email the model re

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 hunt-llm-ai skill

Signals

GitHub stars
790
Forks
138
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
hunt-llm-ai-zyrexnn
Source
github.com/zyrexnn/cybermes