{"skill":{"slug":"dcl-prompt-firewall","displayName":"DCL Prompt Firewall","summary":"Instruction-only input-layer shield for AI agents and LLM pipelines. Detects prompt injection, jailbreak attempts, instruction override, role-switch attacks,...","tags":{"latest":"1.0.2"},"stats":{"comments":0,"downloads":109,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":3},"createdAt":1775878467521,"updatedAt":1776084109339},"latestVersion":{"version":"1.0.2","createdAt":1776083139530,"changelog":"- Refined and streamlined the detection checklist and attack category descriptions for clarity and simplicity.\n- Merged and generalized some attack pattern categories; updated language for plain and concise pattern definitions.\n- Revised output schema to remove input/analysis hashes and deterministic fingerprint, focusing on findings and category status.\n- Updated privacy and pipeline placement sections for clarity and concise instruction.\n- Improved quick-start and usage instructions, reflecting the skill's fully local, instruction-only operation.","license":"MIT-0"},"metadata":null,"owner":{"handle":"daririnch","userId":"s177qzsztsa0qx35zmdc3g65s184c673","displayName":"Dari Rinch","image":"https://avatars.githubusercontent.com/u/161933416?v=4"},"moderation":null}