Unverified50% confidenceFactExact time
AI-Infra-Guard通过五个核心扫描维度保障AI生态安全，包括Agent Scan、Skills Scan、MCP Scan、AI Infra Scan和LLM越狱评估
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/22/2026
First Seen
Valid until: 11/20/2026
Sources
Related Entities
Related Claims
Unverified当前AI安全工具生态包括模型评估工具（如Garak、HarmBench、Purple Llama CyberSecEval）、护栏工具（如Guardrails AI、NeMo Guardrails、LLM Guard）和Agent安全框架（如Invariant Labs的Analyzer）74% similarUnverified腾讯开源了AI-Infra-Guard，定位为全栈AI红队测试平台72% similarUnverifiedAISI对多个前沿模型采用统一框架进行评估，正在推动AI安全评估的标准化进程71% similarPartially Verified英国AI安全研究所（AISI）发布了对OpenAI GPT-5.5的网络安全能力评估报告71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/786727API
curl https://kongchang.com/api/v1/knowledge/claims/786727MCP
get_claim(id=786727)