by caidongyun · AI Tool · ★ 24
AI Agent Security Scanner v6.2.0 企业级 AI Agent 安全扫描工具 📊 核心指标 🎯 快速开始 安装 使用 🔥 v6.2.0 新特性 风险分级体系 Curl 风险分级: 白名单域名 + 敏感参数检测 凭据窃取检测: 攻击链识别 (诱导→混淆→外传) 5 级风险体系: CRITICAL/HIGH/MEDIUM/LOW/INFO 单 Skill 熔断机制 默认阈值: 500 文件/目录 防止恶意软件塞入大量文件拖慢扫描 参数: 规则库优化 去重 88 条规则 (928 → 846) 标准化 419 条 severity 为大写 新增 6 条凭据攻击链规则 (CRED-CHAIN-001006) 📦 发布文件清单 (20 个) 核心模块 (8 个): 规则库 (2 个): — 846 条规则 — 规则优化器 (新增) 引擎模块 (9 个): (8 个检测引擎) 入口 (3 个): — CLI 入口 — Node.js 入口 — 类型定义 文档/配置 (5
| Stars | 24 |
| Forks | 5 |
| Language | Python |
| Category | AI Tool |
| Quality Score | 46.1867172133023/100 |
| Last Updated | 2026-04-28 |
| Created | 2026-03-16 |
| Platforms | python |
| Est. Tokens | ~4970k |
Explore other popular ai tool tools:
agent-security-skill-scanner is an open-source ai tool by caidongyun with 24 GitHub stars.
agent-security-skill-scanner is primarily written in Python.
You can find installation instructions and usage details in the agent-security-skill-scanner GitHub repository at github.com/caidongyun/agent-security-skill-scanner. The project has 24 stars and 5 forks, indicating an active community.