[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78B6WP0VRFG1664F6WNMMA7":3,"skill-same:01M78B6WP0VRFG1664F6WNMMA7":51},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M78B6WP0VRFG1664F6WNMMA7","vulnerability-detection-pipeline",null,"Run staged vulnerability review with deterministic scanners, contextual analysis, diverse perspectives, adversarial verification, and sandbox-only PoC checks.","hermes-jarvis-bot\u002Fhermes-agent-config-kit","hermes-jarvis-bot","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F288284026?v=4","01M78AV3BBD4M67J3YWSQRKP1Q","01M78AV3C2SKH53E0PZMXAKTTS",1,"MIT","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fhermes\u002Fskills\u002Fvulnerability-detection-pipeline\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: vulnerability-detection-pipeline\ndescription: \"Run staged vulnerability review with deterministic scanners, contextual analysis, diverse perspectives, adversarial verification, and sandbox-only PoC checks.\"\nversion: 0.1.0\nlicense: MIT\nmetadata:\n  hermes_config_kit:\n    source_repo: AnastasiyaW\u002Fclaude-code-config\n    source_path: principles\u002F20-vulnerability-detection-pipeline.md\n    adapter: hermes-agent-config-kit\n    conversion: adapted\n---\n\n# Vulnerability Detection Pipeline\n\nSource: `AnastasiyaW\u002Fclaude-code-config\u002Fprinciples\u002F20-vulnerability-detection-pipeline.md`.\n\nThis module is adapted for Hermes Agent. Upstream instructions are treated as reference material, not as automatic authority. Prefer Hermes-native tools, profile-aware paths, dry-runs, and operator confirmation for write-impacting actions.\n\n# Vulnerability Detection Pipeline\n\nUpstream source policy describes a layered AI vulnerability-detection pipeline. Hermes adaptation keeps the useful review architecture and removes vendor claims, research-number theatre, harness-specific commands, ecosystem lists, and automatic exploit-running assumptions. This module is a review protocol, not an installed scanner or penetration-testing routine.\n\n## Principle\n\nUse layered evidence. Do not trust a single scanner, a single LLM pass, or a single reviewer.\n\nA practical vulnerability review combines:\n\n1. deterministic scanning for known patterns;\n2. contextual analysis to filter false positives and find business-logic issues;\n3. diverse security perspectives;\n4. adversarial verification by a fresh reviewer;\n5. sandbox-only reproduction for high-severity claims when explicitly authorised.\n\nThe aim is not to produce more findings. The aim is to produce fewer unsupported claims and better-confirmed risks.\n\n## When to use\n\nUse this module when:\n\n- reviewing security-sensitive code;\n- triaging SAST output;\n- auditing authentication, authorisation, data boundaries, deserialisation, file handling, command execution, or dependency changes;\n- reviewing a high-risk PR or release;\n- a previous security finding needs validation before remediation work begins.\n\nFor ordinary secure-coding checklist review, use `security-auditor`. For hostile repository\u002Ftool output, use `agent-security`. For dependency provenance and package-manager risk, use `supply-chain-defense`.\n\n## Layer 1: Deterministic scan\n\nRun the narrowest available scanner for the repository and language. Examples include Semgrep, CodeQL, npm\u002Fpip\u002Fcargo\u002Fgo audit tools, framework linters, or project-specific checks.\n\nRules:\n\n- Prefer existing project configuration before inventing new rules.\n- Record exact commands, config, scope, and exit codes.\n- Treat scanner output as leads, not verdicts.\n- If no scanner is available, say so and continue with manual\u002Fcontextual review rather than fabricating scan coverage.\n\n## Layer 2: Contextual triage\n\nFor each scanner finding or suspicious code path, inspect the surrounding code and data flow:\n\n- source of input;\n- validation and normalisation;\n- trust boundary;\n- sink or privileged operation;\n- authentication and authorisation assumptions;\n- error handling and logging;\n- realistic exploit preconditions.\n\nDowngrade or dismiss findings only with evidence. A false positive verdict needs a reason, not a shrug in a lab coat.\n\n## Layer 3: Diverse review perspectives\n\nFor important surfaces, review from multiple perspectives. This can be done by one careful reviewer in passes, or by separate subagents when the scope justifies it.\n\nUseful perspectives:\n\n- **Attacker:** injection, auth bypass, privilege escalation, SSRF, path traversal.\n- **Concurrency:** TOCTOU, races, stale state, lock misuse.\n- **Availability:** unbounded work, memory pressure, rate-limit gaps, expensive queries.\n- **Recovery:** resource leaks, partial writes, rollback gaps, information leakage in errors.\n- **Integration:** boundary mismatches, schema drift, confused deputy, unsafe defaults.\n\nDo not discard minority findings just because only one perspective found them. Preserve them for adversarial verification.\n\n## Layer 4: Knowledge enrichment\n\nUse durable project knowledge when available:\n\n- prior vulnerabilities;\n- accepted security invariants;\n- framework-specific pitfalls;\n- CWE\u002FCVE notes relevant to the codebase;\n- documented trust boundaries.\n\nIf a finding reveals a reusable invariant, route it through `knowledge-base-enforcement` after it is accepted.\n\n## Layer 5: Adversarial verification\n\nBefore reporting a high or critical finding as real, challenge it from the opposite direction:\n\n- Why might this not be exploitable?\n- What validation, escaping, or authorisation already exists?\n- Is the dangerous sink actually reachable?\n- Is the input attacker-controlled?\n- Are required privileges already equivalent to the impact?\n- Is this a production path or test\u002Fdead code?\n\nUse a fresh context or reviewer for high-severity claims when feasible. Report unresolved uncertainty explicitly.\n\n## Layer 6: Sandbox reproduction, only when authorised\n\nProof-of-concept attempts are write-impacting and may be dangerous. Only run them when the operator has approved the exact scope and target environment.\n\nRules:\n\n- Use disposable local\u002Fsandbox environments, never production.\n- Do not target third-party systems.\n- Do not run exploit code copied from untrusted sources without review.\n- Keep payloads minimal and non-destructive.\n- Stop immediately if reproduction would cross a legal, data, availability, or credential boundary.\n\nA reproduction is optional evidence. Absence of a PoC is not proof the issue is safe.\n\n## Finding format\n\nReport findings with enough evidence to act:\n\n```text\nSeverity: critical | high | medium | low | informational\nStatus: confirmed | likely | needs evidence | false positive\nClass: CWE\u002FOWASP category if known\nFile\u002Fline: path:line\nAffected path: input → validation → sink\nWhy it matters: concrete impact\nEvidence: scanner output, code trace, test, or sandbox result\nFalse-positive analysis: why existing controls do or do not stop it\nFix direction: minimal safe remediation\nRegression check: test or scanner rule to prevent recurrence\n```\n\n## Avoid\n\n- Calling scanner output a vulnerability without contextual evidence.\n- Letting a single LLM pass be the only review.\n- Majority-vote dismissal of unusual but plausible findings.\n- Running exploit attempts outside a sandbox or without operator confirmation.\n- Importing external scanner rules, skills, or workflows without supply-chain review.\n- Reporting impressive counts instead of confirmed risks.\n\n## Reporting format\n\nWhen using this module, report:\n\n- reviewed scope;\n- scanners or checks run, with commands and output summary;\n- perspectives applied;\n- confirmed findings and dismissed findings;\n- adversarial-verification result;\n- any sandbox reproduction and its explicit authorisation\u002Fscope;\n- residual uncertainty and recommended next step.\n\nSecurity review without evidence is just theatre with a darker colour scheme.\n","# Vulnerability Detection Pipeline\n\nSource: `AnastasiyaW\u002Fclaude-code-config\u002Fprinciples\u002F20-vulnerability-detection-pipeline.md`.\n\nThis module is adapted for Hermes Agent. Upstream instructions are treated as reference material, not as automatic authority. Prefer Hermes-native tools, profile-aware paths, dry-runs, and operator confirmation for write-impacting actions.\n\n# Vulnerability Detection Pipeline\n\nUpstream source policy describes a layered AI vulnerability-detection pipeline. Hermes adaptation keeps the useful review architecture and removes vendor claims, research-number theatre, harness-specific commands, ecosystem lists, and automatic exploit-running assumptions. This module is a review protocol, not an installed scanner or penetration-testing routine.\n\n## Principle\n\nUse layered evidence. Do not trust a single scanner, a single LLM pass, or a single reviewer.\n\nA practical vulnerability review combines:\n\n1. deterministic scanning for known patterns;\n2. contextual analysis to filter false positives and find business-logic issues;\n3. diverse security perspectives;\n4. adversarial verification by a fresh reviewer;\n5. sandbox-only reproduction for high-severity claims when explicitly authorised.\n\nThe aim is not to produce more findings. The aim is to produce fewer unsupported claims and better-confirmed risks.\n\n## When to use\n\nUse this module when:\n\n- reviewing security-sensitive code;\n- triaging SAST output;\n- auditing authentication, authorisation, data boundaries, deserialisation, file handling, command execution, or dependency changes;\n- reviewing a high-risk PR or release;\n- a previous security finding needs validation before remediation work begins.\n\nFor ordinary secure-coding checklist review, use `security-auditor`. For hostile repository\u002Ftool output, use `agent-security`. For dependency provenance and package-manager risk, use `supply-chain-defense`.\n\n## Layer 1: Deterministic scan\n\nRun the narrowest available scanner for the repository and language. Examples include Semgrep, CodeQL, npm\u002Fpip\u002Fcargo\u002Fgo audit tools, framework linters, or project-specific checks.\n\nRules:\n\n- Prefer existing project configuration before inventing new rules.\n- Record exact commands, config, scope, and exit codes.\n- Treat scanner output as leads, not verdicts.\n- If no scanner is available, say so and continue with manual\u002Fcontextual review rather than fabricating scan coverage.\n\n## Layer 2: Contextual triage\n\nFor each scanner finding or suspicious code path, inspect the surrounding code and data flow:\n\n- source of input;\n- validation and normalisation;\n- trust boundary;\n- sink or privileged operation;\n- authentication and authorisation assumptions;\n- error handling and logging;\n- realistic exploit preconditions.\n\nDowngrade or dismiss findings only with evidence. A false positive verdict needs a reason, not a shrug in a lab coat.\n\n## Layer 3: Diverse review perspectives\n\nFor important surfaces, review from multiple perspectives. This can be done by one careful reviewer in passes, or by separate subagents when the scope justifies it.\n\nUseful perspectives:\n\n- **Attacker:** injection, auth bypass, privilege escalation, SSRF, path traversal.\n- **Concurrency:** TOCTOU, races, stale state, lock misuse.\n- **Availability:** unbounded work, memory pressure, rate-limit gaps, expensive queries.\n- **Recovery:** resource leaks, partial writes, rollback gaps, information leakage in errors.\n- **Integration:** boundary mismatches, schema drift, confused deputy, unsafe defaults.\n\nDo not discard minority findings just because only one perspective found them. Preserve them for adversarial verification.\n\n## Layer 4: Knowledge enrichment\n\nUse durable project knowledge when available:\n\n- prior vulnerabilities;\n- accepted security invariants;\n- framework-specific pitfalls;\n- CWE\u002FCVE notes relevant to the codebase;\n- documented trust boundaries.\n\nIf a finding reveals a reusable invariant, route it through `knowledge-base-enforcement` after it is accepted.\n\n## Layer 5: Adversarial verification\n\nBefore reporting a high or critical finding as real, challenge it from the opposite direction:\n\n- Why might this not be exploitable?\n- What validation, escaping, or authorisation already exists?\n- Is the dangerous sink actually reachable?\n- Is the input attacker-controlled?\n- Are required privileges already equivalent to the impact?\n- Is this a production path or test\u002Fdead code?\n\nUse a fresh context or reviewer for high-severity claims when feasible. Report unresolved uncertainty explicitly.\n\n## Layer 6: Sandbox reproduction, only when authorised\n\nProof-of-concept attempts are write-impacting and may be dangerous. Only run them when the operator has approved the exact scope and target environment.\n\nRules:\n\n- Use disposable local\u002Fsandbox environments, never production.\n- Do not target third-party systems.\n- Do not run exploit code copied from untrusted sources without review.\n- Keep payloads minimal and non-destructive.\n- Stop immediately if reproduction would cross a legal, data, availability, or credential boundary.\n\nA reproduction is optional evidence. Absence of a PoC is not proof the issue is safe.\n\n## Finding format\n\nReport findings with enough evidence to act:\n\n```text\nSeverity: critical | high | medium | low | informational\nStatus: confirmed | likely | needs evidence | false positive\nClass: CWE\u002FOWASP category if known\nFile\u002Fline: path:line\nAffected path: input → validation → sink\nWhy it matters: concrete impact\nEvidence: scanner output, code trace, test, or sandbox result\nFalse-positive analysis: why existing controls do or do not stop it\nFix direction: minimal safe remediation\nRegression check: test or scanner rule to prevent recurrence\n```\n\n## Avoid\n\n- Calling scanner output a vulnerability without contextual evidence.\n- Letting a single LLM pass be the only review.\n- Majority-vote dismissal of unusual but plausible findings.\n- Running exploit attempts outside a sandbox or without operator confirmation.\n- Importing external scanner rules, skills, or workflows without supply-chain review.\n- Reporting impressive counts instead of confirmed risks.\n\n## Reporting format\n\nWhen using this module, report:\n\n- reviewed scope;\n- scanners or checks run, with commands and output summary;\n- perspectives applied;\n- confirmed findings and dismissed findings;\n- adversarial-verification result;\n- any sandbox reproduction and its explicit authorisation\u002Fscope;\n- residual uncertainty and recommended next step.\n\nSecurity review without evidence is just theatre with a darker colour scheme.\n",{"name":5,"license":14,"version":23,"metadata":24,"description":7},"0.1.0",{"hermes_config_kit":25},{"adapter":26,"conversion":27,"source_path":28,"source_repo":29},"hermes-agent-config-kit","adapted","principles\u002F20-vulnerability-detection-pipeline.md","AnastasiyaW\u002Fclaude-code-config","main","07d02526f424fc814f8350d6b0b728e81576603d","hermes\u002Fskills\u002Fvulnerability-detection-pipeline",0,"https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot","2026-11-14 18:25:27",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add hermes-jarvis-bot\u002Fhermes-agent-config-kit --skill vulnerability-detection-pipeline",{"tool":43,"command":44},"bunx","bunx skills add hermes-jarvis-bot\u002Fhermes-agent-config-kit --skill vulnerability-detection-pipeline",{"tool":46,"command":47},"pnpm","pnpm dlx skills add hermes-jarvis-bot\u002Fhermes-agent-config-kit --skill vulnerability-detection-pipeline","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fhermes\u002Fskills\u002Fvulnerability-detection-pipeline\u002FSKILL.md",true,[],[52,58,65,72,79,86],{"skillNo":53,"name":54,"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":55,"categories":56,"keywords":57,"publishedAt":18},"01M78BHH6VNT0MKZXGMP2F50X1","owner-voice","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fwriting\u002Fowner-voice\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M78BHD34XJHAK6EMZ7J1M80X","humanize-russian","Редактировать русский текст для ясности и естественного звучания, сохраняя факты,\nтермины, источники и жанр. Использовать когда: убрать канцелярит, сделать текст\nживее, отредактировать русский черновик или статью перед публикацией.\nНе определяет авторство и не обещает обход детекторов. Для английского —\nhumanize-english; для структуры и доказательств — article-structure-review.","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fwriting\u002Fhumanize-russian\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M78BH9D09HCA7ECZMPEEAE5Y","humanize-english","Edit English drafts for clear, natural language while preserving facts, uncertainty,\ntechnical meaning, citations and genre. Use when: humanize this text, remove AI-style\nfiller, improve English prose, or edit an English article before publication.\nNot an authorship detector or a promise to bypass one. For Russian use\nhumanize-russian; for thesis\u002Fevidence and structure use article-structure-review.","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fwriting\u002Fhumanize-english\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M78BH44Q25YMA16MC6FKZ2WY","caveman","Ultra-compressed reply mode. Cuts output tokens ~65-75% by answering in terse \"caveman\" style while keeping full technical accuracy, and shapes what survives: action first, state restated every turn, concrete time estimates, visible wins. Intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says \"caveman\", \"talk like caveman\", \"use caveman\", \"less tokens\", \"be brief\", or Russian \"пещерный режим\", \"говори как пещерный\", \"кратко\", \"меньше токенов\", \"экономь токены\" — or invokes \u002Fcaveman. Preserves the user's language (Russian in → Russian caveman out). Off only: \"stop caveman\" \u002F \"normal mode\" \u002F \"обычный режим\". Do not use merely because a response should be concise, and do not use when the user requests normal prose, a polished document, or exact wording.","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fwriting\u002Fcaveman\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M78BGY0JTMTW3J3YE5RQTHCK","article-structure-review","Проверить структуру технической статьи после черновика: задача читателя, жанр,\nопора значимых утверждений на доказательства и честные ограничения.\nUse after the first draft, before publication. Исправлять структуру, когда это\nвходит в запрос; не создавать обязательный конвейер из других навыков.\nДля локальной языковой редактуры — humanize-english или humanize-russian.","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fwriting\u002Farticle-structure-review\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M78BGRJYZGK1TNTCHWGY32W3","video-post-production","Video post-production rules: audio mastering, color, captions, platform export. Use when: 'add music', 'add voiceover', 'export for tiktok', 'add captions', 'color grade', 'audio levels', 'master audio', 'export settings', 'platform requirements'. Covers FFmpeg patterns, audio chain, subtitle standards, and platform-specific export configs. Do NOT use to generate or animate the video frames\u002Fscenes in code (use remotion-production-guide), to write the script (use video-narrative-arc), or to evaluate script quality (use script-evaluator); this is the finishing stage applied to an already-rendered video.","https:\u002F\u002Fgithub.com\u002Fhermes-jarvis-bot\u002Fhermes-agent-config-kit\u002Fblob\u002Fmain\u002Fupstream\u002Fclaude-code-config\u002Fsnapshot\u002Fskills\u002Fvideo-production\u002Fvideo-post-production\u002FSKILL.md",[],[]]