[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78CJ433Q67REWM911803CMF":3,"skill-same:01M78CJ433Q67REWM911803CMF":66},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M78CJ433Q67REWM911803CMF","code-security-review",null,"Scans source code for security vulnerabilities — injection flaws, authentication bypasses, hardcoded secrets, XSS, and more — then filters false positives and ranks findings by severity and confidence. Supports all programming languages. Uses a three-phase audit-filter-report workflow with customizable scan categories and filtering rules. Use when the user asks for a security review, vulnerability scan, security audit, code security check, or wants to find security bugs in their code.","NitrogenT7\u002Fkimi-code-security","NitrogenT7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F289338396?v=4","01M78CFQ0EEM77XTKQSACG4MCE","01M78CFQ17MCHBS0YCKT2SCBYN",19,"MIT","https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclaude-code-security-skills\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: code-security-review\ndescription: \"Scans source code for security vulnerabilities — injection flaws, authentication bypasses, hardcoded secrets, XSS, and more — then filters false positives and ranks findings by severity and confidence. Supports all programming languages. Uses a three-phase audit-filter-report workflow with customizable scan categories and filtering rules. Use when the user asks for a security review, vulnerability scan, security audit, code security check, or wants to find security bugs in their code.\"\n---\n\n# Code Security Review Skill\n\nThis skill follows a strictly ordered, three-phase process: audit, filter, then report. Complete all phases in sequence — do not report findings until filtering is complete.\n\n---\n\n## Skill Components\n\nBefore starting, read all of the following resource files:\n\n| Resource | Path | Read Requirement |\n|----------|------|-----------------|\n| **Audit Prompt** | `resources\u002Faudit-prompt.md` | MUST read before Phase 1 |\n| **Hard Exclusion Patterns** | `resources\u002Fhard-exclusion-patterns.md` | MUST read before Phase 2 |\n| **False Positive Filtering Rules** | `resources\u002Ffiltering-rules.md` | MUST read before Phase 2 |\n| **Customization Guide** | `resources\u002Fcustomization-guide.md` | Read if project-specific rules are needed |\n\n---\n\n## Execution Process\n\n---\n\n### Phase 1: Security Audit\n\n**Goal:** Produce a raw list of candidate findings. Cast a wide net — do not filter at this stage.\n\n1. Read `resources\u002Faudit-prompt.md` before starting analysis.\n2. Execute the three-phase analysis defined in that document:\n   - **Phase 1a — Codebase Context Research**: Security frameworks, auth patterns, threat model.\n   - **Phase 1b — Comparative Analysis**: Compare code against secure patterns, flag deviations.\n   - **Phase 1c — Vulnerability Assessment**: Trace data flows, injection points, privilege boundaries.\n3. Produce a raw findings list in this internal format (not shown to user yet):\n\n```\nRAW FINDING #N\n- Title: \u003Cshort title>\n- File: \u003Cpath:line>\n- Category: \u003Ce.g. path_traversal, sql_injection, rce>\n- Severity: HIGH \u002F MEDIUM \u002F LOW\n- Description: \u003Cwhat the bug is>\n- Attack Path: \u003Chow an attacker exploits it step by step>\n```\n\n**Checkpoint:** Phase 1 is complete when you have a full raw findings list (can be 0 items).\n\n---\n\n### Phase 2: Filter Findings\n\n**Goal:** Remove false positives. Apply this phase to every item from Phase 1, even if a finding seems obviously valid.\n\n#### Step 2a — Hard Exclusion Pass\n\nRead `resources\u002Fhard-exclusion-patterns.md`. For each raw finding, check:\n\n- Does the title or description match any hard exclusion pattern (DOS, rate limiting, resource management, open redirect, memory safety in non-C\u002FC++, regex injection, SSRF in HTML)?\n- Is the file a Markdown (`.md`) file?\n\nIf YES → mark finding as **`EXCLUDED (Hard Pattern)`** with the matching rule name.\n\n#### Step 2b — AI Filtering Pass\n\nRead `resources\u002Ffiltering-rules.md`. For each non-excluded finding, produce this table row:\n\n| # | Title | Hard Excl? | Precedent Hit? | Concrete Attack Path? | Confidence (1-10) | Decision | Reason |\n|---|-------|-----------|----------------|-----------------------|-------------------|----------|--------|\n| 1 | ... | No | No | Yes | 9 |  KEEP | Directly exploitable, specific code path |\n| 2 | ... | No | UUID unguessable (Precedent #2) | Conditional | 5 |  EXCLUDE | UUID ID guessing required |\n\n**Confidence scoring uses the 1-10 scale from `filtering-rules.md`:**\n\n| Score | Meaning | Action |\n|-------|---------|--------|\n| 1-3 | Low confidence, likely false positive | **EXCLUDE** |\n| 4-6 | Medium confidence, needs investigation | **EXCLUDE** (unless very concrete) |\n| 7-10 | High confidence, likely true vulnerability | **KEEP** |\n\n**Rule:** Any finding with Confidence \u003C 7 is excluded.\n\n**Checkpoint:** Phase 2 is complete when every raw finding has a row in the filter table with a KEEP\u002FEXCLUDE decision.\n\n---\n\n### Phase 3: Report (Only KEPT findings)\n\n**Goal:** Output only the findings that survived Phase 2 filtering. Output the filter table first, then the detailed findings.\n\n#### Filter Summary Table (always show this)\n\nShow the Phase 2 table so the reader can see the filtering decisions.\n\n#### Detailed Finding Report (only KEPT items)\n\nFor each KEPT finding, output:\n\n```\n## Vuln N: \u003CCategory>: `\u003Cfile:line>`\n\n* Severity: HIGH \u002F MEDIUM \u002F LOW\n* Confidence: \u003C1-10 score> \u002F 10\n* Description: \u003Cwhat the vulnerability is>\n* Exploit Scenario: \u003Cconcrete step-by-step attack>\n* Recommendation: \u003Cspecific fix>\n```\n\n#### Non-Findings Summary\n\nList EXCLUDED findings briefly:\n\n```\n## Excluded Findings (N total)\n| # | Title | Reason |\n|---|-------|--------|\n| 1 | Missing rate limiting | Hard exclusion: rate limiting |\n```\n\n---\n\n## Severity Reference\n\n| Severity | Criteria |\n|----------|----------|\n| **HIGH** | Directly exploitable: RCE, data breach, authentication bypass |\n| **MEDIUM** | Requires specific conditions but has significant impact |\n| **LOW** | Defense-in-depth issues or lower-impact vulnerabilities |\n\n","# Code Security Review Skill\n\nThis skill follows a strictly ordered, three-phase process: audit, filter, then report. Complete all phases in sequence — do not report findings until filtering is complete.\n\n---\n\n## Skill Components\n\nBefore starting, read all of the following resource files:\n\n| Resource | Path | Read Requirement |\n|----------|------|-----------------|\n| **Audit Prompt** | `resources\u002Faudit-prompt.md` | MUST read before Phase 1 |\n| **Hard Exclusion Patterns** | `resources\u002Fhard-exclusion-patterns.md` | MUST read before Phase 2 |\n| **False Positive Filtering Rules** | `resources\u002Ffiltering-rules.md` | MUST read before Phase 2 |\n| **Customization Guide** | `resources\u002Fcustomization-guide.md` | Read if project-specific rules are needed |\n\n---\n\n## Execution Process\n\n---\n\n### Phase 1: Security Audit\n\n**Goal:** Produce a raw list of candidate findings. Cast a wide net — do not filter at this stage.\n\n1. Read `resources\u002Faudit-prompt.md` before starting analysis.\n2. Execute the three-phase analysis defined in that document:\n   - **Phase 1a — Codebase Context Research**: Security frameworks, auth patterns, threat model.\n   - **Phase 1b — Comparative Analysis**: Compare code against secure patterns, flag deviations.\n   - **Phase 1c — Vulnerability Assessment**: Trace data flows, injection points, privilege boundaries.\n3. Produce a raw findings list in this internal format (not shown to user yet):\n\n```\nRAW FINDING #N\n- Title: \u003Cshort title>\n- File: \u003Cpath:line>\n- Category: \u003Ce.g. path_traversal, sql_injection, rce>\n- Severity: HIGH \u002F MEDIUM \u002F LOW\n- Description: \u003Cwhat the bug is>\n- Attack Path: \u003Chow an attacker exploits it step by step>\n```\n\n**Checkpoint:** Phase 1 is complete when you have a full raw findings list (can be 0 items).\n\n---\n\n### Phase 2: Filter Findings\n\n**Goal:** Remove false positives. Apply this phase to every item from Phase 1, even if a finding seems obviously valid.\n\n#### Step 2a — Hard Exclusion Pass\n\nRead `resources\u002Fhard-exclusion-patterns.md`. For each raw finding, check:\n\n- Does the title or description match any hard exclusion pattern (DOS, rate limiting, resource management, open redirect, memory safety in non-C\u002FC++, regex injection, SSRF in HTML)?\n- Is the file a Markdown (`.md`) file?\n\nIf YES → mark finding as **`EXCLUDED (Hard Pattern)`** with the matching rule name.\n\n#### Step 2b — AI Filtering Pass\n\nRead `resources\u002Ffiltering-rules.md`. For each non-excluded finding, produce this table row:\n\n| # | Title | Hard Excl? | Precedent Hit? | Concrete Attack Path? | Confidence (1-10) | Decision | Reason |\n|---|-------|-----------|----------------|-----------------------|-------------------|----------|--------|\n| 1 | ... | No | No | Yes | 9 |  KEEP | Directly exploitable, specific code path |\n| 2 | ... | No | UUID unguessable (Precedent #2) | Conditional | 5 |  EXCLUDE | UUID ID guessing required |\n\n**Confidence scoring uses the 1-10 scale from `filtering-rules.md`:**\n\n| Score | Meaning | Action |\n|-------|---------|--------|\n| 1-3 | Low confidence, likely false positive | **EXCLUDE** |\n| 4-6 | Medium confidence, needs investigation | **EXCLUDE** (unless very concrete) |\n| 7-10 | High confidence, likely true vulnerability | **KEEP** |\n\n**Rule:** Any finding with Confidence \u003C 7 is excluded.\n\n**Checkpoint:** Phase 2 is complete when every raw finding has a row in the filter table with a KEEP\u002FEXCLUDE decision.\n\n---\n\n### Phase 3: Report (Only KEPT findings)\n\n**Goal:** Output only the findings that survived Phase 2 filtering. Output the filter table first, then the detailed findings.\n\n#### Filter Summary Table (always show this)\n\nShow the Phase 2 table so the reader can see the filtering decisions.\n\n#### Detailed Finding Report (only KEPT items)\n\nFor each KEPT finding, output:\n\n```\n## Vuln N: \u003CCategory>: `\u003Cfile:line>`\n\n* Severity: HIGH \u002F MEDIUM \u002F LOW\n* Confidence: \u003C1-10 score> \u002F 10\n* Description: \u003Cwhat the vulnerability is>\n* Exploit Scenario: \u003Cconcrete step-by-step attack>\n* Recommendation: \u003Cspecific fix>\n```\n\n#### Non-Findings Summary\n\nList EXCLUDED findings briefly:\n\n```\n## Excluded Findings (N total)\n| # | Title | Reason |\n|---|-------|--------|\n| 1 | Missing rate limiting | Hard exclusion: rate limiting |\n```\n\n---\n\n## Severity Reference\n\n| Severity | Criteria |\n|----------|----------|\n| **HIGH** | Directly exploitable: RCE, data breach, authentication bypass |\n| **MEDIUM** | Requires specific conditions but has significant impact |\n| **LOW** | Defense-in-depth issues or lower-impact vulnerabilities |\n\n",{"name":5,"description":7},"main","cac122702fd7c1bb910d4331d42d31f4d65ef199",".agents\u002Fskills\u002Fclaude-code-security-skills",1,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security","https:\u002F\u002Fgithub.com\u002FNitrogenT7","2026-09-23 16:08:07",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add NitrogenT7\u002Fkimi-code-security --skill code-security-review",{"tool":36,"command":37},"bunx","bunx skills add NitrogenT7\u002Fkimi-code-security --skill code-security-review",{"tool":39,"command":40},"pnpm","pnpm dlx skills add NitrogenT7\u002Fkimi-code-security --skill code-security-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclaude-code-security-skills\u002FSKILL.md",true,[44,50,54,58,62],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"README.md","REFERENCE","参考文档",1170,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclaude-code-security-skills\u002FREADME.md",{"path":51,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":52,"sourceHtmlUrl":53},"resources\u002Faudit-prompt.md",4751,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclaude-code-security-skills\u002Fresources\u002Faudit-prompt.md",{"path":55,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":56,"sourceHtmlUrl":57},"resources\u002Fcustomization-guide.md",4889,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclaude-code-security-skills\u002Fresources\u002Fcustomization-guide.md",{"path":59,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":60,"sourceHtmlUrl":61},"resources\u002Ffiltering-rules.md",6447,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclaude-code-security-skills\u002Fresources\u002Ffiltering-rules.md",{"path":63,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":64,"sourceHtmlUrl":65},"resources\u002Fhard-exclusion-patterns.md",5021,"https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fclaude-code-security-skills\u002Fresources\u002Fhard-exclusion-patterns.md",[67,74,81,88,94,101],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":18},"01M78CM022SAPQANCX0CYBBZD8","kimi-webbridge","Kimi WebBridge lets AI control the user's real browser — navigate, click, type, read, screenshot, and interact with any website using the user's actual login sessions. Use this skill whenever the user wants to interact with websites, automate browser tasks, scrape web content, or perform any action requiring a real browser. Also use when the user mentions \"browser\", \"webpage\", \"open URL\", \"screenshot\", or asks to read\u002Finteract with any website. Use even for simple-sounding browser requests — the daemon handles all complexity.","https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002Fplugins\u002Fofficial\u002Fkimi-webbridge\u002Fskills\u002Fkimi-webbridge\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M78CKTEFA3QGTBQ3XYAKMCRK","kimi-datasource","Universal data-source assistant for stocks (Wind, S&P, SEC EDGAR), macro (World Bank, IMF, FRED, NBS), Chinese government data and standards (GB\u002FHB\u002FDB\u002FTT), corporate, academic, legal, WHO\u002FFAO\u002FOECD and other IGO data, financial news (Xinhua, Caixin).\nThis plugin exposes tools via MCP server `plugin-kimi-datasource_data`; call them in the flow `mcp__plugin-kimi-datasource_data__get_data_source_desc` → `mcp__plugin-kimi-datasource_data__call_data_source_tool`.","https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002Fplugins\u002Fofficial\u002Fkimi-datasource\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M78CKSF8Q6FGM97MJ7ZD095K","golden-skill","Golden fixture skill","https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002Fpackages\u002Fmigration-legacy\u002Ftest\u002Ffixtures\u002Fgolden\u002F.kimi\u002Fskills\u002Fgolden-skill\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":18},"01M78CKRHACG31TNA9266YY8YR","tools","https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002Fpackages\u002Fagent-core-v2\u002Fsrc\u002Ffeatures\u002Fskill\u002Ftools\u002Fskill.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":18},"01M78CKNZ2549R5P70N4JMT1FT","review","Analyze the available skill set and recommend candidate groups that could be consolidated into sub-skill bundles. Read-only — proposes a plan, does not move files.","https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002Fpackages\u002Fagent-core-v2\u002Fsrc\u002Ffeatures\u002Fskill\u002Fcatalog\u002Fbuiltin\u002Fsub-skill\u002Freview\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":18},"01M78CKKHZZHB0BEY72HXGTJE6","consolidate","Apply an approved sub-skill grouping by moving user-specified skills into a parent bundle, with timestamped backups of every modified directory.","https:\u002F\u002Fgithub.com\u002FNitrogenT7\u002Fkimi-code-security\u002Fblob\u002Fmain\u002Fpackages\u002Fagent-core-v2\u002Fsrc\u002Ffeatures\u002Fskill\u002Fcatalog\u002Fbuiltin\u002Fsub-skill\u002Fconsolidate\u002FSKILL.md",[],[]]