[KongchangAI]
Unverified50% confidenceFactExact time

无载荷技能攻击通过技能的元数据、描述文本、命名结构或调用逻辑的组合,诱导智能体在特定上下文中触发非预期的危险行为

1
Sources
50%
Confidence
Long-term
Relevance
7/6/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/113888
API
curl https://kongchang.com/api/v1/knowledge/claims/113888
MCP
get_claim(id=113888)