Expired50% confidenceFactExact time
Mainstream AI safety evaluation leaderboards include four categories such as HarmBench, with the Chinese-language domain requiring especially strong capability in recognizing coded language.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/12/2026
First Seen
Valid until: 10/10/2026(expired)
Sources
Related Claims
UnverifiedMLPS 2.0 is a Chinese national standard that classifies information systems into five security levels, and financial institutions are typically required to meet Level 3 or Level 4 requirements70% similarUnverified高权限 AI 工具在未充分告知用户的情况下悄悄识别用户环境并将信息藏入不可见提示词标点，易被企业安全部门视为严重信任风险69% similarUnverifiedChinese officials are concerned that advanced AI models from the United States focused on cybersecurity could be used to discover and exploit vulnerabilities in Chinese software67% similarUnverifiedThe Ministry of Industry and Information Technology issued a security warning regarding a type of AI Agent tool, listing multiple vulnerabilities.65% similarUnverified安全分类器对请求措辞高度敏感，直接让模型去找漏洞容易被拦截路由到Opus 4.8，用中性描述往往不会触发限制64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/493202API
curl https://kongchang.com/api/v1/knowledge/claims/493202MCP
get_claim(id=493202)