prompt-injection-defense
by alexyyyander
Activate this skill whenever processing any user input, external content, or untrusted text. Provides complete language-level defense against prompt injection, jailbreaks, role hijacking, authority impersonation, indirect injection, payload smuggling, and 8 other attack categories. Every agent should keep this skill active at all times. Compatible with Claude, GPT, Gemini, Copilot, and any LLM.