[KongchangAI]
Unverified50% confidenceFactExact time

通过精心设计的越狱提示词(Jailbreak Prompts),攻击者可绕过主流LLM的安全护栏使其生成有害内容

1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/7/2026
First Seen
Valid until: 10/5/2026

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/144272
API
curl https://kongchang.com/api/v1/knowledge/claims/144272
MCP
get_claim(id=144272)