[KongchangAI]
Unverified50% confidenceFactExact time

Koreshield 会在模型采取行动之前检查数据泄露、帮助文档中的隐藏指令(prompt injection)、策略漂移以及不安全的智能体操作

1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/23/2026
First Seen
Valid until: 12/22/2026

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/943870
API
curl https://kongchang.com/api/v1/knowledge/claims/943870
MCP
get_claim(id=943870)