Unverified65% confidenceOpinionTime unknown
Kimi和MiniMax等国产模型在安全场景下的道德限制仍然偏高，容易拒绝回答甚至封号
1
Sources
65%
Confidence
Medium-term (~90 days)
Relevance
6/2/2026
First Seen
Valid until: 8/31/2026
Sources
AI渗透测试实战：DeepSeek配合三大Agent挖漏洞效果对比
bilibili大白哥AI与安全
Related Entities
Cite This Claim
Stable URI
https://kongchang.com/claim/37529API
curl https://kongchang.com/api/v1/knowledge/claims/37529MCP
get_claim(id=37529)