Garcia R, Li Q, Baker A, Wu F. Jailbreak-Resilient LLM Agents through Instruction Hierarchy, Input Gating, and Self-Verification. J.I.T.I.E [Internet]. 2024 Dec. 31 [cited 2026 Oct. 8];1(1):12-31. Available from: https://journal.jci.co.id/jitie/article/view/818