R. Garcia, Q. Li, A. Baker, and F. Wu, “Jailbreak-Resilient LLM Agents through Instruction Hierarchy, Input Gating, and Self-Verification”, J.I.T.I.E, vol. 1, no. 1, pp. 12–31, Dec. 2024, Accessed: Oct. 08, 2026. [Online]. Available: https://journal.jci.co.id/jitie/article/view/818