[KongchangAI]
Unverified60% confidenceBenchmarkExact time

无防护措施的Sonnet 5底层模型对提示注入攻击表现出极强抵抗力,被攻破概率不到1%

2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
7/8/2026
First Seen
Valid until: 10/6/2026

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/248324
API
curl https://kongchang.com/api/v1/knowledge/claims/248324
MCP
get_claim(id=248324)