[KongchangAI]
Verified65% confidenceFactExact time

提示注入(Prompt Injection)攻击者可通过构造特殊输入诱导Agent执行非预期操作

3
Sources
65%
Confidence
Long-term
Relevance
7/6/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/112620
API
curl https://kongchang.com/api/v1/knowledge/claims/112620
MCP
get_claim(id=112620)