[KongchangAI]
Unverified60% confidenceFactExact time

提示词注入攻击(Prompt Injection)可通过精心构造的用户输入诱导模型忽略系统提示词的约束

2
Sources
60%
Confidence
Long-term
Relevance
7/5/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/112308
API
curl https://kongchang.com/api/v1/knowledge/claims/112308
MCP
get_claim(id=112308)