[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CF596WQ1R4V8YA78RPYCZ7":3,"skill-same:01M6CF596WQ1R4V8YA78RPYCZ7":110},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":33,"publishedAt":53,"linkOnly":54,"markdownContent":55,"markdownBody":56,"frontMatter":57,"refName":58,"commitSha":59,"skillDirectory":60,"forksCount":61,"repositoryHtmlUrl":62,"repositoryHomepageUrl":63,"ownerHtmlUrl":64,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":65,"install":66,"resources":79},"01M6CF596WQ1R4V8YA78RPYCZ7","security",null,"Defensive security engineering judgment, distilled from a stronger model - invoke when THREAT MODELING a system or feature; making security-relevant design decisions (auth, crypto, trust boundaries, attack surface); reviewing code for vulnerabilities (injection, IDOR, secrets, the OWASP classes); hardening operations (secrets management, detection, patching, incident response); or judging whether a security control\u002Fprogram is real or theater. Also invoke BEFORE any offensive-flavored request (pentest, exploit, credential testing) to apply the authorization gate. Also invoke when designing, reviewing, or hardening an LLM\u002Fagent system that reads untrusted content or holds tool\u002FMCP access (prompt injection, excessive agency, MCP supply chain).","telagod\u002Fcode-abyss","telagod","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F39987513?v=4","01M6CF4EH93PP5CWH3J34Z66DP","01M6CF4EN6W4QFXK3PRE9W29X8",244,"MIT","https:\u002F\u002Fgithub.com\u002Ftelagod\u002Fcode-abyss\u002Fblob\u002Fmain\u002Fskills\u002F_kernel\u002Fsecurity\u002FSKILL.md",[17,22,25,30],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":26,"categoryName":27,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":31,"categoryName":32,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000032","设计师",[5,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52],"injection","mcp access","threat","pentest","exploit","model","access","secrets","secrets management","patching","testing","owasp","code","auth","incident response","threat modeling","prompt injection","MCP","design","2026-11-10 10:12:30",false,"---\nuser-invocable: false\nname: security\ndescription: Defensive security engineering judgment, distilled from a stronger model - invoke when THREAT MODELING a system or feature; making security-relevant design decisions (auth, crypto, trust boundaries, attack surface); reviewing code for vulnerabilities (injection, IDOR, secrets, the OWASP classes); hardening operations (secrets management, detection, patching, incident response); or judging whether a security control\u002Fprogram is real or theater. Also invoke BEFORE any offensive-flavored request (pentest, exploit, credential testing) to apply the authorization gate. Also invoke when designing, reviewing, or hardening an LLM\u002Fagent system that reads untrusted content or holds tool\u002FMCP access (prompt injection, excessive agency, MCP supply chain).\n---\n\n# Security — scope gate, threat model, design, review, operations, traps, agentic AI\n\nRule content lives in the seven files below; this SKILL.md only routes\n(`doctrine\u002F04-maintenance.md` governs edits to this bundle too).\n\n**First, always:** `scope.md` §1 — the authorization gate. It fires on ANY request\nmentioning exploits, payloads, bypassing auth\u002FWAF\u002Ffilters, cracking, brute force,\ncredential\u002Fpassword testing, scanning a target, or accessing a system the requester\ndidn't build in this session — recognize the moment even when the ask is phrased as\n\"just write a script.\" Defensive work proceeds; offensive-flavored work needs\ncorroborated authorization context; some requests are refused regardless of framing.\nPass the gate before applying anything else in this bundle.\n\n## Route by moment\n\n| You are about to… | Read (in this folder) |\n|---|---|\n| Judge scope — fires on ANY mention of exploits, payloads, bypassing auth\u002FWAF, cracking, brute force, credential testing, scanning a target, or reaching a system the requester didn't build here | `scope.md` §1 |\n| Decide what to protect, from whom, and where to spend | `threat-model.md` |\n| Design auth, trust boundaries, crypto use, or a system's security posture | `design.md` |\n| Review code for vulnerabilities, or report security findings | `review.md` |\n| Handle secrets, hardening, logging\u002Fdetection, dependencies, incidents | `operate.md` |\n| Assess whether a control or security program is real; name why it smells | `traps.md` |\n| Design, review, or harden a system where an LLM\u002Fagent reads untrusted content or holds tool\u002FMCP access (prompt injection, excessive agency, MCP supply chain) | `agentic.md` |\n\nA new system usually runs `threat-model.md` (four questions) → `design.md` →\n`review.md` before ship → `operate.md` in production.\n\n## Scope and neighbors\n\nSecurity judgment for building and defending systems. The application-level security\nfloor (input validation, per-object authz in `backend\u002Foperate.md` §5; rate limits in\n`backend\u002Foperate.md` §7) also lives in the backend bundle — this bundle is the deeper\ntreatment. Agentic AI security (prompt injection, the lethal trifecta, tool-privilege\nboundaries, MCP supply chain) is `agentic.md` — it extends this bundle's design\u002Freview\u002F\noperate rules to agents, not a replacement for them. General verification\ndiscipline is `methods\u002Fverify.md`; whether to delegate → `doctrine`.\n\n## The stance\n\n**Attackers take the cheapest path; defenders must be honest about which door is open.**\nThreat model before controls (`threat-model.md`), assume breach (`scope.md` §3), make\nthe safe way the easy way (`design.md` §3) — and never confuse a control that exists\nwith a control that works (`traps.md` meta-signal). A clean review means \"nothing found\nwhere I looked,\" never \"secure\" (`scope.md` §5).\n","# Security — scope gate, threat model, design, review, operations, traps, agentic AI\n\nRule content lives in the seven files below; this SKILL.md only routes\n(`doctrine\u002F04-maintenance.md` governs edits to this bundle too).\n\n**First, always:** `scope.md` §1 — the authorization gate. It fires on ANY request\nmentioning exploits, payloads, bypassing auth\u002FWAF\u002Ffilters, cracking, brute force,\ncredential\u002Fpassword testing, scanning a target, or accessing a system the requester\ndidn't build in this session — recognize the moment even when the ask is phrased as\n\"just write a script.\" Defensive work proceeds; offensive-flavored work needs\ncorroborated authorization context; some requests are refused regardless of framing.\nPass the gate before applying anything else in this bundle.\n\n## Route by moment\n\n| You are about to… | Read (in this folder) |\n|---|---|\n| Judge scope — fires on ANY mention of exploits, payloads, bypassing auth\u002FWAF, cracking, brute force, credential testing, scanning a target, or reaching a system the requester didn't build here | `scope.md` §1 |\n| Decide what to protect, from whom, and where to spend | `threat-model.md` |\n| Design auth, trust boundaries, crypto use, or a system's security posture | `design.md` |\n| Review code for vulnerabilities, or report security findings | `review.md` |\n| Handle secrets, hardening, logging\u002Fdetection, dependencies, incidents | `operate.md` |\n| Assess whether a control or security program is real; name why it smells | `traps.md` |\n| Design, review, or harden a system where an LLM\u002Fagent reads untrusted content or holds tool\u002FMCP access (prompt injection, excessive agency, MCP supply chain) | `agentic.md` |\n\nA new system usually runs `threat-model.md` (four questions) → `design.md` →\n`review.md` before ship → `operate.md` in production.\n\n## Scope and neighbors\n\nSecurity judgment for building and defending systems. The application-level security\nfloor (input validation, per-object authz in `backend\u002Foperate.md` §5; rate limits in\n`backend\u002Foperate.md` §7) also lives in the backend bundle — this bundle is the deeper\ntreatment. Agentic AI security (prompt injection, the lethal trifecta, tool-privilege\nboundaries, MCP supply chain) is `agentic.md` — it extends this bundle's design\u002Freview\u002F\noperate rules to agents, not a replacement for them. General verification\ndiscipline is `methods\u002Fverify.md`; whether to delegate → `doctrine`.\n\n## The stance\n\n**Attackers take the cheapest path; defenders must be honest about which door is open.**\nThreat model before controls (`threat-model.md`), assume breach (`scope.md` §3), make\nthe safe way the easy way (`design.md` §3) — and never confuse a control that exists\nwith a control that works (`traps.md` meta-signal). A clean review means \"nothing found\nwhere I looked,\" never \"secure\" (`scope.md` §5).\n",{"name":5,"description":7,"user-invocable":54},"main","2544577cf03a67522466450000731e52c64a5184","skills\u002F_kernel\u002Fsecurity",35,"https:\u002F\u002Fgithub.com\u002Ftelagod\u002Fcode-abyss","https:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002Fcode-abyss","https:\u002F\u002Fgithub.com\u002Ftelagod","2026-07-19 23:15:32",{"source":8,"skillName":5,"commands":67,"prompt":77,"zipAvailable":78},[68,71,74],{"tool":69,"command":70},"npx","npx skills add telagod\u002Fcode-abyss --skill security",{"tool":72,"command":73},"bunx","bunx skills add telagod\u002Fcode-abyss --skill security",{"tool":75,"command":76},"pnpm","pnpm dlx skills add telagod\u002Fcode-abyss --skill security","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftelagod\u002Fcode-abyss\u002Fblob\u002Fmain\u002Fskills\u002F_kernel\u002Fsecurity\u002FSKILL.md",true,[80,86,90,94,98,102,106],{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"agentic.md","REFERENCE","参考文档",7139,"https:\u002F\u002Fgithub.com\u002Ftelagod\u002Fcode-abyss\u002Fblob\u002Fmain\u002Fskills\u002F_kernel\u002Fsecurity\u002Fagentic.md",{"path":87,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":88,"sourceHtmlUrl":89},"design.md",6257,"https:\u002F\u002Fgithub.com\u002Ftelagod\u002Fcode-abyss\u002Fblob\u002Fmain\u002Fskills\u002F_kernel\u002Fsecurity\u002Fdesign.md",{"path":91,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":92,"sourceHtmlUrl":93},"operate.md",8613,"https:\u002F\u002Fgithub.com\u002Ftelagod\u002Fcode-abyss\u002Fblob\u002Fmain\u002Fskills\u002F_kernel\u002Fsecurity\u002Foperate.md",{"path":95,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":96,"sourceHtmlUrl":97},"review.md",12443,"https:\u002F\u002Fgithub.com\u002Ftelagod\u002Fcode-abyss\u002Fblob\u002Fmain\u002Fskills\u002F_kernel\u002Fsecurity\u002Freview.md",{"path":99,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":100,"sourceHtmlUrl":101},"scope.md",5119,"https:\u002F\u002Fgithub.com\u002Ftelagod\u002Fcode-abyss\u002Fblob\u002Fmain\u002Fskills\u002F_kernel\u002Fsecurity\u002Fscope.md",{"path":103,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":104,"sourceHtmlUrl":105},"threat-model.md",5032,"https:\u002F\u002Fgithub.com\u002Ftelagod\u002Fcode-abyss\u002Fblob\u002Fmain\u002Fskills\u002F_kernel\u002Fsecurity\u002Fthreat-model.md",{"path":107,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":108,"sourceHtmlUrl":109},"traps.md",9287,"https:\u002F\u002Fgithub.com\u002Ftelagod\u002Fcode-abyss\u002Fblob\u002Fmain\u002Fskills\u002F_kernel\u002Fsecurity\u002Ftraps.md",[111,118,126,133,144,154],{"skillNo":112,"name":113,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":53},"01M6CF94Y2R0JYCS270NC9BKM5","parse-error","https:\u002F\u002Fgithub.com\u002Ftelagod\u002Fcode-abyss\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fskill-contract\u002Fparse-error\u002Ftools\u002Fparse-error\u002FSKILL.md",[],[117],"parse error",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":53},"01M6CF925B128W5YAHWVYSJQTG","multi-script","too many scripts","https:\u002F\u002Fgithub.com\u002Ftelagod\u002Fcode-abyss\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fskill-contract\u002Fmulti-script\u002Ftools\u002Fmulti-script\u002FSKILL.md",[],[125],"multi script",{"skillNo":127,"name":128,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":53},"01M6CF8ZYT3KZ4ZZAATFJH0DV4","missing-description","https:\u002F\u002Fgithub.com\u002Ftelagod\u002Fcode-abyss\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fskill-contract\u002Fmissing-description\u002Ftools\u002Fmissing-description\u002FSKILL.md",[],[132],"missing description",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":53},"01M6CF8XB2Z8NAPYW3W7S7KW1S","invalid-tools","invalid tool name","https:\u002F\u002Fgithub.com\u002Ftelagod\u002Fcode-abyss\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fskill-contract\u002Finvalid-tools\u002Ftools\u002Finvalid-tools\u002FSKILL.md",[],[140,141,142,143],"Tools","invalid tools","Bash","tool",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":151,"publishedAt":53},"01M6CF8TTPYFV83HSF057F95QM","clash-skill","first duplicate","https:\u002F\u002Fgithub.com\u002Ftelagod\u002Fcode-abyss\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fskill-contract\u002Fduplicate\u002Ftools\u002Falpha\u002FSKILL.md",[150],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[152,153],"clash skill","first",{"skillNo":155,"name":146,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":160,"publishedAt":53},"01M6CF8RAHFEPXNB6SWBR2T49M","second duplicate","https:\u002F\u002Fgithub.com\u002Ftelagod\u002Fcode-abyss\u002Fblob\u002Fmain\u002Ftest\u002Ffixtures\u002Fskill-contract\u002Fduplicate\u002Fdomains\u002Falpha\u002FSKILL.md",[159],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[152]]