[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AC4G3FV5FJ54PRV761XJKB":3,"skill-same:01M6AC4G3FV5FJ54PRV761XJKB":82},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":6,"updatedAt":53,"install":54,"resources":67},"01M6AC4G3FV5FJ54PRV761XJKB","attack-path-analysis",null,"Use when Codex is already in the attack-path-analysis phase of a security scan or the user explicitly asks to trace a security finding from source to sink and calibrate severity. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.","openai\u002Fcodex-security","openai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F14957082?v=4","01M6AC29YGCR4S2NTJFV0G8B81","OpenAI","01M6AC4B22Q8KPN8SGEAJYRB0N",13511,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex-security\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex-security\u002Fskills\u002Fattack-path-analysis\u002FSKILL.md",[],[19,20,21,22,23,24,5,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"analysis","path","attack path analysis","scan","phase","when","repository","patch","security scan","use","attack-path","trigger","calibrate","for","severity","branch","do","as","commit","pr","codex","2026-11-10 10:12:30",false,"---\nname: attack-path-analysis\ndescription: Use when Codex is already in the attack-path-analysis phase of a security scan or the user explicitly asks to trace a security finding from source to sink and calibrate severity. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.\n---\n\n# Security Attack Path Analysis\n\nDetermine whether each supplied finding has a supported attacker path, what impact it has, and whether it is reportable. Before creating or retaining files, read `..\u002F..\u002Freferences\u002Fartifact-storage.md`.\n\n## Establish the attack path\n\nFor a scan phase, use its per-scan threat model and candidate set from `..\u002F..\u002Freferences\u002Fscan-artifacts.md`. Preserve supplied input paths. If a required scan artifact is unavailable, report the missing input.\n\nFor standalone analysis, use the supplied finding, repository, threat model or security policy, and context. A per-scan artifact is not required. State material assumptions and ask for missing context only when it prevents a meaningful assessment.\n\n1. Establish the in-scope attacker, affected product surface, entry point, controlled input, security boundary, and sensitive operation. Trace each step using repository evidence and supplied observations of the target.\n2. Identify relevant controls and the strongest counterevidence. Explain what they establish, which prerequisites remain, and whether the exact claimed boundary is crossed.\n3. Assess impact and likelihood from those facts. Apply [references\u002Fseverity-policy.md](references\u002Fseverity-policy.md) for the final decision. When the scan supplies a severity rubric, use it to grade reportable findings and retain `ignore` for candidates without security impact. Keep facts, severity calibration, and the final policy decision distinguishable in the result.\n4. Return an explicit decision for every eligible candidate, including ignored or deferred candidates. Do not replace a supported instance with a neighboring finding or lose its root-control location.\n\nFor an imported AWS Continuum issue, read `source_data.evidence_artifacts` in the supplied finding evidence. A `VALIDATION_EVIDENCE` artifact's `body.validationEvidence` may establish a step the repository cannot show. Match the tested target, attacker privileges, and observed effect to the claimed path. For a bundled issue, use `perFindingResults` and `flowVerdicts` when present to identify the relevant finding and flow. An HTTP `exploitArtifact` can establish reachability from the tested position. An `executedProof` establishes what ran in its test environment. `sourceAnalysis` records a static inference, and an `exploitable` verdict alone does not demonstrate deployed reachability. Cite the artifact ID and the observation that supports or contradicts the step.\n\nTreat supplied artifacts as evidence. Access the network only when the user has expressly authorized it; an offline scan never accesses the network. Do not invent unsupported attack chains. Missing deployment or public-ingress evidence can limit confidence without defeating an otherwise supported finding.\n\n## Scan integration\n\nStandard scans and Deep Scan workers assess attack paths within their ordinary Standard scan workflow; neither invokes this separate phase skill.\n\n### Compact Workbench Diff\n\nWhen a workbench-backed `$security-diff-scan` has a `scanId`:\n\n- Load the per-scan threat model and all validated candidates with `list_codex_security_candidates({ scanId, cursor?, limit? })`.\n- Analyze every `reportable` or `deferred` validation candidate. Preserve candidate identity and existing discovery and validation fields.\n- Submit every decision together with `record_candidate_attack_paths({ scanId, attackPaths: [{ candidateId, attackPath }] })`. Submit `attackPaths: []` when no candidate enters this phase. The tool preserves the stored candidate order.\n- These nested decisions are the complete phase output. Do not create duplicate reports, receipts, or manual ledgers.\n\n### Other phase-based scans\n\nUse the active workflow's report and receipt paths in `..\u002F..\u002Freferences\u002Fscan-artifacts.md`. Every candidate entering this phase must have an explicit decision and a receipt with its ID, facts or exact proof gap, and report reference. Record ignored candidates before excluding them from the surviving finding set.\n\nFor repository-wide or scoped-path scans, include validation closure rows marked `reportable` or `survives: yes`, even if discovery did not assign a polished finding number. Preserve affected entrypoint\u002Fwrapper, root-control, sink, and concrete-implementation locations supplied by validation.\n\n## Output\n\nFor standalone analysis, follow the caller's format or return a concise assessment per finding. Scan phases use their output contract above. Include:\n\n- title and supplied candidate, instance, and ledger identities;\n- precise affected locations and attacker-to-impact steps;\n- relevant facts from [references\u002Fattack-path-facts.md](references\u002Fattack-path-facts.md);\n- controls, counterevidence, prerequisites, and material proof gaps;\n- impact, likelihood, calibrated severity, and final policy decision with their reasons.\n\nRetain enough evidence to explain both surviving and suppressed findings. Apply the severity policy to the established facts rather than reopening discovery or substituting a different attack story.\n","# Security Attack Path Analysis\n\nDetermine whether each supplied finding has a supported attacker path, what impact it has, and whether it is reportable. Before creating or retaining files, read `..\u002F..\u002Freferences\u002Fartifact-storage.md`.\n\n## Establish the attack path\n\nFor a scan phase, use its per-scan threat model and candidate set from `..\u002F..\u002Freferences\u002Fscan-artifacts.md`. Preserve supplied input paths. If a required scan artifact is unavailable, report the missing input.\n\nFor standalone analysis, use the supplied finding, repository, threat model or security policy, and context. A per-scan artifact is not required. State material assumptions and ask for missing context only when it prevents a meaningful assessment.\n\n1. Establish the in-scope attacker, affected product surface, entry point, controlled input, security boundary, and sensitive operation. Trace each step using repository evidence and supplied observations of the target.\n2. Identify relevant controls and the strongest counterevidence. Explain what they establish, which prerequisites remain, and whether the exact claimed boundary is crossed.\n3. Assess impact and likelihood from those facts. Apply [references\u002Fseverity-policy.md](references\u002Fseverity-policy.md) for the final decision. When the scan supplies a severity rubric, use it to grade reportable findings and retain `ignore` for candidates without security impact. Keep facts, severity calibration, and the final policy decision distinguishable in the result.\n4. Return an explicit decision for every eligible candidate, including ignored or deferred candidates. Do not replace a supported instance with a neighboring finding or lose its root-control location.\n\nFor an imported AWS Continuum issue, read `source_data.evidence_artifacts` in the supplied finding evidence. A `VALIDATION_EVIDENCE` artifact's `body.validationEvidence` may establish a step the repository cannot show. Match the tested target, attacker privileges, and observed effect to the claimed path. For a bundled issue, use `perFindingResults` and `flowVerdicts` when present to identify the relevant finding and flow. An HTTP `exploitArtifact` can establish reachability from the tested position. An `executedProof` establishes what ran in its test environment. `sourceAnalysis` records a static inference, and an `exploitable` verdict alone does not demonstrate deployed reachability. Cite the artifact ID and the observation that supports or contradicts the step.\n\nTreat supplied artifacts as evidence. Access the network only when the user has expressly authorized it; an offline scan never accesses the network. Do not invent unsupported attack chains. Missing deployment or public-ingress evidence can limit confidence without defeating an otherwise supported finding.\n\n## Scan integration\n\nStandard scans and Deep Scan workers assess attack paths within their ordinary Standard scan workflow; neither invokes this separate phase skill.\n\n### Compact Workbench Diff\n\nWhen a workbench-backed `$security-diff-scan` has a `scanId`:\n\n- Load the per-scan threat model and all validated candidates with `list_codex_security_candidates({ scanId, cursor?, limit? })`.\n- Analyze every `reportable` or `deferred` validation candidate. Preserve candidate identity and existing discovery and validation fields.\n- Submit every decision together with `record_candidate_attack_paths({ scanId, attackPaths: [{ candidateId, attackPath }] })`. Submit `attackPaths: []` when no candidate enters this phase. The tool preserves the stored candidate order.\n- These nested decisions are the complete phase output. Do not create duplicate reports, receipts, or manual ledgers.\n\n### Other phase-based scans\n\nUse the active workflow's report and receipt paths in `..\u002F..\u002Freferences\u002Fscan-artifacts.md`. Every candidate entering this phase must have an explicit decision and a receipt with its ID, facts or exact proof gap, and report reference. Record ignored candidates before excluding them from the surviving finding set.\n\nFor repository-wide or scoped-path scans, include validation closure rows marked `reportable` or `survives: yes`, even if discovery did not assign a polished finding number. Preserve affected entrypoint\u002Fwrapper, root-control, sink, and concrete-implementation locations supplied by validation.\n\n## Output\n\nFor standalone analysis, follow the caller's format or return a concise assessment per finding. Scan phases use their output contract above. Include:\n\n- title and supplied candidate, instance, and ledger identities;\n- precise affected locations and attacker-to-impact steps;\n- relevant facts from [references\u002Fattack-path-facts.md](references\u002Fattack-path-facts.md);\n- controls, counterevidence, prerequisites, and material proof gaps;\n- impact, likelihood, calibrated severity, and final policy decision with their reasons.\n\nRetain enough evidence to explain both surviving and suppressed findings. Apply the severity policy to the established facts rather than reopening discovery or substituting a different attack story.\n",{"name":5,"description":7},"main","2911786f243f08fd61ad854f5c527e7b0c404ccc","plugins\u002Fcodex-security\u002Fskills\u002Fattack-path-analysis",1051,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex-security","https:\u002F\u002Fdevelopers.openai.com\u002Fcodex\u002Fsecurity","https:\u002F\u002Fgithub.com\u002Fopenai","https:\u002F\u002Fopenai.com\u002F","2026-11-15 01:14:45",{"source":8,"skillName":5,"commands":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add openai\u002Fcodex-security --skill attack-path-analysis",{"tool":60,"command":61},"bunx","bunx skills add openai\u002Fcodex-security --skill attack-path-analysis",{"tool":63,"command":64},"pnpm","pnpm dlx skills add openai\u002Fcodex-security --skill attack-path-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex-security\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex-security\u002Fskills\u002Fattack-path-analysis\u002FSKILL.md",true,[68,74,78],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"agents\u002Fopenai.yaml","REFERENCE","参考文档",261,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex-security\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex-security\u002Fskills\u002Fattack-path-analysis\u002Fagents\u002Fopenai.yaml",{"path":75,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fattack-path-facts.md",1585,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex-security\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex-security\u002Fskills\u002Fattack-path-analysis\u002Freferences\u002Fattack-path-facts.md",{"path":79,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fseverity-policy.md",2644,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex-security\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex-security\u002Fskills\u002Fattack-path-analysis\u002Freferences\u002Fseverity-policy.md",[83,105,127,135,156,170],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":40},"01M6AC5YCQRMA998JYF1YQZ22X","vulnerability-writeup","Turn vulnerability notes, disclosure reports, PoCs, source code, or Codex Security findings into self-contained vulnerability reports with clearly supported claims. Use for one vulnerability or a disclosure campaign; a Codex Security scan is optional.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex-security\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex-security\u002Fskills\u002Fvulnerability-writeup\u002FSKILL.md",[],[90,91,39,92,93,94,95,27,28,96,97,22,98,99,100,101,32,102,103,104],"vulnerability writeup","vulnerability","security","notes","code","codex security","campaign","reports","self","with","codex security scan","claims","source","self-contained","source code",{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":40},"01M6AC5VVAAEE1N7RD44GM74B8","verify-fix","Use only when the user explicitly requests verification that a security fix remediates a reported vulnerability. Do not invoke automatically while implementing fixes, reviewing ordinary code changes, or running tests. Do not use for non-security fixes, candidate finding validation, or full repository scans.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex-security\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex-security\u002Fskills\u002Fverify-fix\u002FSKILL.md",[],[112,113,114,92,94,115,116,117,91,28,118,35,119,120,121,32,122,123,124,125,24,126],"verify fix","verify","fix","validation","verification","running tests","only","tests","requests","implementing","changes","fixes","candidate","invoke","running",{"skillNo":128,"name":115,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":40},"01M6AC5SF5X4MYQ8YSTMWMCT8S","Use when Codex is already in the validation phase of a security scan or the user explicitly asks to determine whether one or more candidate security findings are valid. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex-security\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex-security\u002Fskills\u002Fvalidation\u002FSKILL.md",[],[115,39,92,133,37,38,27,25,34,28,26,35,22,36,30,134,32,124,23,24],"valid","more",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":40},"01M6AC5PS8CWNQPC4JP6DH1MFQ","triage-finding","Triage supplied or imported security findings against a repository using its security policy and static code evidence. Accepts scanner reports, advisories, GitHub findings, and Jira or Linear tickets. Do not use for discovery, duplicate triage, runtime validation, or fixes.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex-security\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex-security\u002Fskills\u002Ftriage-finding\u002FSKILL.md",[],[142,143,144,92,145,146,147,94,115,148,25,149,28,150,97,151,35,152,153,154,32,123,155],"triage","triage finding","github","policy","jira","runtime validation","linear","discovery","evidence","scanner","imported","runtime","duplicate","static",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":162,"publishedAt":40},"01M6AC5M0N76KYA78936Q7VV34","track-findings","Track validated Codex Security findings in Linear, Jira, GitHub issues, or draft GitHub security advisories. Supports issue batches, duplicate checks, and reviewed writes. Do not use for scans or fixes.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex-security\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex-security\u002Fskills\u002Ftrack-findings\u002FSKILL.md",[],[163,164,144,39,92,146,165,166,148,95,28,167,35,168,154,169,32,123],"track findings","track","github issues","issues","issue","draft","batches",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":176,"publishedAt":40},"01M6AC5GTW07GPK3T0D9S4EDXZ","threat-model","Use when Codex is already in the threat-modeling phase of a security scan, the user explicitly invokes $threat-model, or the user explicitly asks to create, update, or persist a repository threat model. Do not use as the primary trigger for full PR, commit, branch, patch, or repository scans.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fcodex-security\u002Fblob\u002Fmain\u002Fplugins\u002Fcodex-security\u002Fskills\u002Fthreat-model\u002FSKILL.md",[],[177,178,179,39,92,37,38,180,181,27,182,34,28,26,35,22,36,30,183,32,23,24],"threat model","model","threat","create","update","threat-modeling","persist"]