{"id":"d87505e6-42db-4a9b-ae41-8fef4c172808","slug":"clawhub-ebandao777-oss-zhongkui-skill","name":"zhongkui-skill","description":"钟馗.Skill——Agent Skill 安全审查专家。直来直去、快刀斩乱麻，三层审查（静态审计/行为模拟/供应链溯源）覆盖10类风险，输出结构化安全裁定（✅干净/⚠️可疑/🚫恶意）。Use when 用户说\"审查这个Skill\"、\"安全检查\"、\"钟馗看下\"、\"审一下\"、\"查一下这个skill\"、安装Skill前的安全评估、或需要审计SKILL.md的恶意载荷。","canonicalUrl":"https://www.xpersona.co/agent/clawhub-ebandao777-oss-zhongkui-skill","sourceUrl":"https://clawhub.ai/ebandao777-oss/zhongkui-skill","homepage":"https://clawhub.ai/ebandao777-oss/skills/zhongkui-skill","source":"CLAWHUB","vendor":{"slug":"clawhub","label":"Clawhub","url":"https://clawhub.ai/ebandao777-oss/skills/zhongkui-skill"},"protocols":["OPENCLEW"],"capabilities":[],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":"1.0.3","freshnessAt":"2026-10-11T08:48:59.495Z","freshnessLabel":"Oct 11, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"OpenClaw"},{"label":"Freshness","value":"Oct 11, 2026"},{"label":"Vendor","value":"Clawhub"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"1.0.3"}],"factsPreview":[{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Clawhub","href":"https://clawhub.ai/ebandao777-oss/skills/zhongkui-skill","sourceUrl":"https://clawhub.ai/ebandao777-oss/skills/zhongkui-skill","sourceType":"profile","confidence":"medium","observedAt":"2026-10-11T08:48:59.512Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"OpenClaw","href":"https://www.xpersona.co/api/v1/agents/clawhub-ebandao777-oss-zhongkui-skill/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ebandao777-oss-zhongkui-skill/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-10-11T08:48:59.512Z","isPublic":true},{"factKey":"traction","category":"adoption","label":"Adoption signal","value":"1.1K downloads","href":"https://clawhub.ai/ebandao777-oss/zhongkui-skill","sourceUrl":"https://clawhub.ai/ebandao777-oss/zhongkui-skill","sourceType":"profile","confidence":"medium","observedAt":"2026-10-11T08:48:59.512Z","isPublic":true},{"factKey":"latest_release","category":"release","label":"Latest release","value":"1.0.3","href":"https://clawhub.ai/ebandao777-oss/zhongkui-skill","sourceUrl":"https://clawhub.ai/ebandao777-oss/zhongkui-skill","sourceType":"release","confidence":"medium","observedAt":"2026-08-15T17:29:35.986Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/clawhub-ebandao777-oss-zhongkui-skill/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-ebandao777-oss-zhongkui-skill/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["1.1K downloads","Trust evidence available"],"agentCard":{"name":"zhongkui-skill","description":"钟馗.Skill——Agent Skill 安全审查专家。直来直去、快刀斩乱麻，三层审查（静态审计/行为模拟/供应链溯源）覆盖10类风险，输出结构化安全裁定（✅干净/⚠️可疑/🚫恶意）。Use when 用户说\"审查这个Skill\"、\"安全检查\"、\"钟馗看下\"、\"审一下\"、\"查一下这个skill\"、安装Skill前的安全评估、或需要审计SKILL.md的恶意载荷。","source":"CLAWHUB","sourceId":"clawhub:s17en637qww2q9z3kz1ep6w79988dec4:zhongkui-skill","homepage":"https://clawhub.ai/ebandao777-oss/skills/zhongkui-skill","repository":"https://clawhub.ai/ebandao777-oss/zhongkui-skill","documentation":"https://www.xpersona.co/agent/clawhub-ebandao777-oss-zhongkui-skill","protocols":["OPENCLEW"],"examples":[{"kind":"example","language":"text","snippet":"## 钟馗裁定：[✅/⚠️/🚫]\n\n**总分**：XX / 100\n**一句话**：[一句话结论]\n\n### 扣分项\n| 层级 | 检查项 | 风险类型 | 扣分 | 命中内容（行号） |\n|:---|:---|:---|:---|:---|\n| L1 | [项名] | [R编号] | -X | `<file>:L<N>` |\n\n### 未触发项\n[仅列出高危项（R1/R3/R5/R8）的 PASS 状态，其余省略]"},{"kind":"example","language":"text","snippet":"zhongkui-skill/\n├── SKILL.md                           # 技能定义（Agent 加载入口）\n├── README.md                          # 本文件\n├── QUICKSTART.md                      # 快速上手\n├── REFERENCE.md                       # 完整技术参考\n├── zhongkui.py                        # 主审查引擎入口\n├── core/\n│   ├── __init__.py\n│   ├── auditor.py                     # Layer 1 静态审计引擎（52 项）\n│   └── scorer.py                      # 评分计算器\n└── references/\n    ├── agent-skill-security-review.md # 完整方法论（14 篇论文）\n    ├── risk-taxonomy.md               # 10 维风险分类\n    ├── static-audit.md                # 52 项检查清单\n    ├── behavioral-emulation.md        # 18 场景+红队对抗\n    ├── supply-chain.md                # 8 维供应链溯源\n    ├── scoring.md                     # 评分公式与多引擎仲裁\n    ├── fix-strategies.md              # 9 类风险修复策略\n    ├── trust-hierarchy.md             # 5 级信任层级\n    ├── roadmap.md                     # Phase 1-4 落地路线图\n    └── paper-mapping.md               # 论文→模块映射表"}]}}