项目预览
项目数据
项目介绍
Star 增长趋势
本站每日记录该项目 GitHub 星标变化,观测越久曲线越完整
数据来源:GitHub API 逐日快照 · 收录于 2026-08-09 · 当前星标 ★ 105
核心亮点
- 自动化生成对抗性测试场景,无需人工编写大量用例
- 聚焦前沿风险如欺骗、权力寻求,直击安全痛点
- 提供可复现的评估框架,便于社区对比和迭代
不足之处
- 早期项目,文档和社区支持待观察
- 评估场景可能偏学术,实际部署适配需验证
适用场景
- 大模型发布前的安全审计
- AI智能体行为监控与红队测试
- 安全对齐研究的基准测试
替代项目
AgentBench、RSPBench、Inspect AI
上一篇:ai-eval-platform
下一篇:ClawdSecbot
同类项目推荐
ai-privacy-toolkit
开源
给 AI 模型做隐私体检,快速发现合规风险
A toolkit for tools and techniques related to the privacy and compliance of AI model···
SIMURG
开源
流式生成中实时拦截重复、漂移和乱码,不让坏 token 见用户
Zero-leak online detection of LLM decoding corruption and Free Web Search for your A···
vigil-llm
开源
给LLM输入装个安检门,拦截提示注入和越狱攻击
⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large···
skill-validator
开源
一条命令检查 Agent Skill 写得对不对、够不够扎实
Validate Skill content against Agent Skill specification, with additional content de···
Machine_Learning_CTF_Challenges
开源
实战演练AI攻防,用CTF挑战掌握模型攻击与LLM漏洞利用
Hack AI/ML applications — CTF challenges for model attacks, LLMs and AI Agent explo···
prometheus-eval
开源
用 Prometheus 或 GPT-4 自动给 LLM 回复打分,快速筛选最佳模型。
Evaluate your LLM's response with Prometheus and GPT4
getIPIntel
开源
一个 API 查 IP,拦代理、VPN、TOR 和恶意流量
IP Intelligence is a free Proxy VPN TOR and Bad IP detection tool to prevent Fraud, ···
DSBench
开源
测测你的AI助手能不能像数据科学家一样干活
[ICLR 2025] DSBench: How Far are Data Science Agents from Becoming Data Science Expe···
Internal-Safety-Collapse
开源
把AI智能体放进正常代码流程,看它如何自己补出危险操作
[NeurIPS 2026] Safety failures in coding agents and frontier LLMs. Reproducible work···
