Ran H, Foster N, Liang B, Meyer J. Continual Guardrail Learning for Tool-Using LLM Agents: Cross-Benchmark Jailbreak Detection, Indirect Prompt-Injection Filtering, and Utility Preservation. J.I.S.B.T. 2026;2(4):111-121. Accessed August 22, 2026. https://journal.jci.co.id/jisbt/article/view/590