BankBench-MY
A multilingual (EN / Bahasa Malaysia / Manglish) safety evaluation for banking-agent LLMs — does a banking chatbot leak OTPs and account data, process unauthorised transfers, or follow phishing links when conversation register shifts mid-conversation
https://sinarproject.org/projects/enabling-tech/research-fellow-bank-bench-my-safety-of-deploying-llm-agents-in-malaysian-banking-applications/bankbench-my
https://sinarproject.org/projects/enabling-tech/research-fellow-bank-bench-my-safety-of-deploying-llm-agents-in-malaysian-banking-applications/bankbench-my/@@images/image-1200-aaa3b7bb7a27ea1bc2d327bc0a49a55c.png
Research Reports, Working Paper
BankBench-MY
by
Sharifa Noh
—
published
Oct 07, 2026
A multilingual (EN / Bahasa Malaysia / Manglish) safety evaluation for banking-agent LLMs — does a banking chatbot leak OTPs and account data, process unauthorised transfers, or follow phishing links when conversation register shifts mid-conversation
Related Project
Enabling Tech
Output of
Research Fellow: Bank Bench MY Safety of Deploying LLM Agents in Malaysian Banking Applications
