mayubench-en

AI-Native Behavior Benchmark — 48 scenarios × 3 difficulty levels = 144 questions, 8-dimension scoring, measuring whether AI should do things, not whether it...

This skill appears coherent and instruction-only — it contains a self-contained question bank and rubric and does not request credentials or install anything. Before running automated evaluations: 1) inspect the pseudocode/automation section (the file references a pseudocode judge) to ensure it does not call external endpoints or transmit data; 2) do not provide secrets or platform credentials to any automated judge model used with this benchmark; 3) be aware many benchmark items intentionally include adversarial prompt text designed to test prompt-injection resilience — treat those test inputs as potentially manipulative and run them in isolated or non-privileged sessions; 4) if you don't want the agent to autonomously trigger evaluations, restrict skill invocation or disable autonomous invocation in your agent runtime. If you want higher assurance, paste the full pseudocode/automation snippet here for review.

Type: OpenClaw Skill Name: mayubench-en Version: 1.0.0 The bundle is a comprehensive AI behavior benchmark (MayuBench) designed to evaluate model alignment and safety across 144 scenarios. While MayuBench_v1.0.md contains examples of prompt injection and requests for harmful activities (e.g., WiFi cracking in E14-1 or 'Ignore all instructions' in E18-1), these are explicitly presented as test data for benchmarking purposes rather than instructions for the agent to execute. The skill lacks any malicious code, data exfiltration logic, or unauthorized system access.