[KongchangAI]
Unverified50% confidenceFactExact time

间接提示注入攻击中,攻击者只需在RAG会检索到的数据源中植入恶意指令即可操纵模型,传统WAF无法拦截

1
Sources
50%
Confidence
Long-term
Relevance
7/18/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/547721
API
curl https://kongchang.com/api/v1/knowledge/claims/547721
MCP
get_claim(id=547721)