H. Ran, N. Foster, B. Liang, and J. Meyer, “Continual Guardrail Learning for Tool-Using LLM Agents: Cross-Benchmark Jailbreak Detection, Indirect Prompt-Injection Filtering, and Utility Preservation”, J.I.S.B.T, vol. 2, no. 4, pp. 111–121, Aug. 2026, Accessed: Aug. 22, 2026. [Online]. Available: https://journal.jci.co.id/jisbt/article/view/590