[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75PTYPP8PKJP1PA7SS0QMVW":3,"skill-same:01M75PTYPP8PKJP1PA7SS0QMVW":48},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M75PTYPP8PKJP1PA7SS0QMVW","patcher-overview",null,"Stage 4 patch generation playbook. Minimal diffs for validated findings with mandatory patch_verify. Load at patcher-agent startup.","Iwakishirokoshu\u002FHermesUltimate","Iwakishirokoshu","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F194847626?v=4","01M75P4CVGA89TTCE8JGMNAQQ9","Around","01M75P4CWF85V6GVSEFKGGFZ03",0,"MIT","https:\u002F\u002Fgithub.com\u002FIwakishirokoshu\u002FHermesUltimate\u002Fblob\u002Fmain\u002Fstack\u002Fdecepticon-slim\u002Fupstream\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fplugins\u002Fpatcher\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: patcher-overview\ndescription: Stage 4 patch generation playbook. Minimal diffs for validated findings with mandatory patch_verify. Load at patcher-agent startup.\nmetadata:\n  subdomain: orchestration\n  when_to_use: \"patcher stage 4 patch generation minimal diff validated finding patch_verify pipeline\"\n  upstream_ref: \"Decepticon vulnresearch pipeline — stage 4 patcher role\"\n---\n\n# Patcher Skill\n\nYou fix validated findings and prove the fix holds. Minimal diffs, one\nconcern at a time, mandatory `patch_verify` before claiming done.\n\n## Iteration loop\n\n```\nwhile not patched and attempts \u003C 3:\n    1. kg_query(kind=\"vulnerability\", min_severity=\"medium\")\n       → pick validated=True, patched!=True\n    2. Read the function around (file, line)\n    3. Design minimal fix (validate \u002F escape \u002F parameterize \u002F safe API)\n    4. patch_propose(vuln_id, diff, commit_message) → patch_id\n    5. Apply diff via Edit or bash patch\n    6. (optional) bash: run repo tests, abort on failure\n    7. patch_verify(patch_id, poc_command, success_patterns,\n                    test_cmd=optional)\n    8. if status == \"verified\": done\n       elif status == \"tests_failed\": revert, retry\n       elif status == \"regressed\": revert, analyze, retry\n    attempts += 1\n```\n\n## Diff style\n\n- **Unified diff.** Use `git diff --no-color` output or write one by hand.\n- **Minimal hunk.** One concern. No formatting. No renames. No \"while I'm\n  here\" cleanups. No new files (unless adding one regression test).\n- **Safe-API preference.**\n\n| Bug class               | Preferred fix                                        |\n|-------------------------|------------------------------------------------------|\n| SQL injection           | Parameterized query \u002F ORM.filter(), NOT escaping     |\n| Command injection       | Arg-list subprocess, shell=False                     |\n| Path traversal          | `os.path.realpath` + prefix check                    |\n| SSRF                    | Allowlist + resolve → check not private\u002Floopback     |\n| Deserialization         | Switch to safe loader (`yaml.safe_load`, JSON, etc.) |\n| Broken auth             | Move check to pre-hook, not inside handler           |\n| Reflected XSS           | Framework auto-escape, remove `Markup`\u002F`safe`        |\n\n- **Add a regression test** in the same diff when the repo has a test\n  directory for the affected module. One test that exercises the fixed\n  path is sufficient.\n\n## Commit message format\n\nConventional commits. Example:\n\n```\nfix(auth): use constant-time comparison in verify_hmac\n\nPrevents timing side-channel recovery of the HMAC. CWE-208.\n```\n\n## Decisive-completion rule\n\nOnly report \"patched\" after `patch_verify.status == \"verified\"`. A\ngreen test suite is NOT sufficient — the PoC must actually fail.\n\nIf all 3 attempts fail, STOP on the finding, record a note via\n`kg_add_node` on the vuln (`patch_attempts=3, last_failure=...`) and\nreturn to the orchestrator. Do not spiral.\n","# Patcher Skill\n\nYou fix validated findings and prove the fix holds. Minimal diffs, one\nconcern at a time, mandatory `patch_verify` before claiming done.\n\n## Iteration loop\n\n```\nwhile not patched and attempts \u003C 3:\n    1. kg_query(kind=\"vulnerability\", min_severity=\"medium\")\n       → pick validated=True, patched!=True\n    2. Read the function around (file, line)\n    3. Design minimal fix (validate \u002F escape \u002F parameterize \u002F safe API)\n    4. patch_propose(vuln_id, diff, commit_message) → patch_id\n    5. Apply diff via Edit or bash patch\n    6. (optional) bash: run repo tests, abort on failure\n    7. patch_verify(patch_id, poc_command, success_patterns,\n                    test_cmd=optional)\n    8. if status == \"verified\": done\n       elif status == \"tests_failed\": revert, retry\n       elif status == \"regressed\": revert, analyze, retry\n    attempts += 1\n```\n\n## Diff style\n\n- **Unified diff.** Use `git diff --no-color` output or write one by hand.\n- **Minimal hunk.** One concern. No formatting. No renames. No \"while I'm\n  here\" cleanups. No new files (unless adding one regression test).\n- **Safe-API preference.**\n\n| Bug class               | Preferred fix                                        |\n|-------------------------|------------------------------------------------------|\n| SQL injection           | Parameterized query \u002F ORM.filter(), NOT escaping     |\n| Command injection       | Arg-list subprocess, shell=False                     |\n| Path traversal          | `os.path.realpath` + prefix check                    |\n| SSRF                    | Allowlist + resolve → check not private\u002Floopback     |\n| Deserialization         | Switch to safe loader (`yaml.safe_load`, JSON, etc.) |\n| Broken auth             | Move check to pre-hook, not inside handler           |\n| Reflected XSS           | Framework auto-escape, remove `Markup`\u002F`safe`        |\n\n- **Add a regression test** in the same diff when the repo has a test\n  directory for the affected module. One test that exercises the fixed\n  path is sufficient.\n\n## Commit message format\n\nConventional commits. Example:\n\n```\nfix(auth): use constant-time comparison in verify_hmac\n\nPrevents timing side-channel recovery of the HMAC. CWE-208.\n```\n\n## Decisive-completion rule\n\nOnly report \"patched\" after `patch_verify.status == \"verified\"`. A\ngreen test suite is NOT sufficient — the PoC must actually fail.\n\nIf all 3 attempts fail, STOP on the finding, record a note via\n`kg_add_node` on the vuln (`patch_attempts=3, last_failure=...`) and\nreturn to the orchestrator. Do not spiral.\n",{"name":5,"metadata":24,"description":7},{"subdomain":25,"when_to_use":26,"upstream_ref":27},"orchestration","patcher stage 4 patch generation minimal diff validated finding patch_verify pipeline","Decepticon vulnresearch pipeline — stage 4 patcher role","main","c0c483827a963764d5e1a663a9591867d47289e6","stack\u002Fdecepticon-slim\u002Fupstream\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fplugins\u002Fpatcher","https:\u002F\u002Fgithub.com\u002FIwakishirokoshu\u002FHermesUltimate","https:\u002F\u002Fgithub.com\u002FIwakishirokoshu","2026-06-15 13:48:41",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Iwakishirokoshu\u002FHermesUltimate --skill patcher-overview",{"tool":40,"command":41},"bunx","bunx skills add Iwakishirokoshu\u002FHermesUltimate --skill patcher-overview",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Iwakishirokoshu\u002FHermesUltimate --skill patcher-overview","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FIwakishirokoshu\u002FHermesUltimate\u002Fblob\u002Fmain\u002Fstack\u002Fdecepticon-slim\u002Fupstream\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fplugins\u002Fpatcher\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M770W8JDE5EC1TJT4GSDWD78","wps-pixie-dust","WPS Pixie-Dust offline nonce attack (reaver -K \u002F pixiewps) and fallback online PIN brute (bully) to recover the AP's WPA PSK without capturing a handshake.","https:\u002F\u002Fgithub.com\u002FIwakishirokoshu\u002FHermesUltimate\u002Fblob\u002Fmain\u002Fstack\u002Fdecepticon-slim\u002Fupstream\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fwps-pixie-dust\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M770W4B7T5VCVHB88V1F02H1","wpa3-sae","WPA3-SAE transition-mode downgrade (DragonShift), SSID Confusion CVE-2023-52424, Dragonblood side-channels, and SAE captive-portal credential recovery against WPA3-Personal networks.","https:\u002F\u002Fgithub.com\u002FIwakishirokoshu\u002FHermesUltimate\u002Fblob\u002Fmain\u002Fstack\u002Fdecepticon-slim\u002Fupstream\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fwpa3-sae\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M770W093C8FAV8S34K8VB6T9","wpa2-psk","WPA\u002FWPA2-PSK handshake capture via targeted deauth + PMKID (no deauth required) + offline hashcat cracking. The most common consumer\u002FSMB encryption mode in 2026.","https:\u002F\u002Fgithub.com\u002FIwakishirokoshu\u002FHermesUltimate\u002Fblob\u002Fmain\u002Fstack\u002Fdecepticon-slim\u002Fupstream\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fwpa2-psk\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M770VTNAQGZ3D0RQVFEKTE8Z","wpa-enterprise-eap","WPA\u002FWPA2\u002FWPA3-Enterprise (802.1X\u002FEAP) rogue-RADIUS evil-twin for MSCHAPv2 capture, GTC downgrade, and PEAP relay. MSCHAPv2 capture equals a NetNTLM hash — the primary wireless on-ramp to Active Directory.","https:\u002F\u002Fgithub.com\u002FIwakishirokoshu\u002FHermesUltimate\u002Fblob\u002Fmain\u002Fstack\u002Fdecepticon-slim\u002Fupstream\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fwpa-enterprise-eap\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M770VNG05ZX3CV84R9GX8PJN","krack-fragattacks","KRACK key-reinstallation (CVE-2017-13077..13082) and FragAttacks fragmentation\u002Faggregation flaws (CVE-2020-24586..24588, CVE-2020-26139..26147) against legacy or embedded 802.11 supplicants with poor patch cadence.","https:\u002F\u002Fgithub.com\u002FIwakishirokoshu\u002FHermesUltimate\u002Fblob\u002Fmain\u002Fstack\u002Fdecepticon-slim\u002Fupstream\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fkrack-fragattacks\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M770VHFH7N192V56PFSRXF5K","evil-twin-karma","Evil-twin rogue AP with KARMA\u002FMana PNL-probe response, captive-portal credential capture, and post-association MITM for PSK\u002Fopen networks. Distinct from wpa-enterprise-eap which targets 802.1X.","https:\u002F\u002Fgithub.com\u002FIwakishirokoshu\u002FHermesUltimate\u002Fblob\u002Fmain\u002Fstack\u002Fdecepticon-slim\u002Fupstream\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fevil-twin-karma\u002FSKILL.md",[],[]]