Unverified90% confidenceFactTime unknown
Raptor同时支持进攻性安全（红队渗透测试）、防御性安全（蓝队威胁分析）和安全研究三大场景
1
Sources
90%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAgent security should be quantitatively evaluated using three core metrics: attack success rate, over-refusal rate, and attack type classification accuracy.67% similarUnverifiedVICE actively simulates attack surface probing of an application's externally exposed interactive interfaces, with a methodology derived from penetration testing and red team exercises rather than traditional passive compliance checklists.65% similarUnverified对抗式审查借鉴了安全领域的红队测试、架构评审中的魔鬼代言人技术和测试驱动开发（TDD）等工程实践65% similarUnverifiedThe industrial Agent security interception layer should follow the defense-in-depth principle, divided into four levels: syntax validation, logic validation, state validation, and historical pattern validation.64% similarUnverifiedcMCP 强调事后可证明性，与聚焦事前拦截和事中监控的现有 AI 安全方案构成互补的纵深防御64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/28874API
curl https://kongchang.com/api/v1/knowledge/claims/28874MCP
get_claim(id=28874)