[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75PRQP0HXVGKVBWTZ3FTY9Z":3,"skill-same:01M75PRQP0HXVGKVBWTZ3FTY9Z":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},"01M75PRQP0HXVGKVBWTZ3FTY9Z","detector-overview",null,"Stage 2 vulnerability detector playbook. Reads source around CANDIDATE nodes and promotes real bugs to VULNERABILITY + HYPOTHESIS. Read-only. Load at detector-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\u002Fdetector\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: detector-overview\ndescription: Stage 2 vulnerability detector playbook. Reads source around CANDIDATE nodes and promotes real bugs to VULNERABILITY + HYPOTHESIS. Read-only. Load at detector-agent startup.\nmetadata:\n  subdomain: orchestration\n  when_to_use: \"detector stage 2 vulnerability candidate vulnerability hypothesis read-only source-read pipeline\"\n  upstream_ref: \"Decepticon vulnresearch pipeline — stage 2 detector role\"\n---\n\n# Detector Skill\n\nYou promote scanner candidates into real `VULNERABILITY` nodes — or\nreject them as false positives — by reading the surrounding source.\nYou have no bash and no scanner tools. Only graph CRUD and source reads.\n\n## Per-candidate decision flow\n\n1. Pull candidate: `kg_query(kind=\"candidate\", limit=20)`.\n2. For each candidate (highest score first):\n   a. Read ±30 lines around `path:line`. Prefer function boundaries.\n   b. Identify: source? sink? taint path? sanitizer?\n   c. Load the relevant playbook: `\u002Fskills\u002Fstandard\u002Fanalyst\u002F\u003Cvuln-class>\u002FSKILL.md`.\n      Available classes: sql-injection, ssrf, deserialization, idor, ssti,\n      xss, xxe, path-traversal, command-injection, prototype-pollution,\n      prompt-injection, auth-bypass.\n   d. Decide: promote, reject, or hypothesis-only.\n3. Emit.\n\n## Promotion template\n\n```python\nvuln = kg_add_node(\n    \"vulnerability\",\n    \"SQLi in product search\",\n    props='{\"key\":\"app.py:search_products:sqli\",\"severity\":\"high\",'\n          '\"file\":\"\u002Fworkspace\u002Ftarget\u002Fapp.py\",\"line\":142,\"cwe\":[\"CWE-89\"],'\n          '\"source\":\"request.args.get(\\\\\"q\\\\\")\",\"sink\":\"cursor.execute\",'\n          '\"evidence\":\"cursor.execute(f\\\\\"SELECT * FROM products WHERE name LIKE \\'%{q}%\\'\\\\\")\"}',\n)\nhyp = kg_add_node(\n    \"hypothesis\",\n    \"Unsanitized query param flows into f-string SQL\",\n    props='{\"key\":\"app.py:search_products:sqli:hyp\"}',\n)\nkg_add_edge(vuln_id, candidate_id, \"derived_from\")\nkg_add_edge(hyp_id, vuln_id, \"mapped_to\")\n```\n\n## Rejection template\n\nSame `kg_add_node` call with the SAME `key`, plus `status=\"rejected\"`\nand `reason=\"sanitized via html.escape before sink\"`. Idempotent — the\ngraph upsert merges the rejection on top of the original candidate.\n\n## Severity calibration\n\n| Signal                                                     | Severity  |\n|------------------------------------------------------------|-----------|\n| Unauth + external input + dangerous sink + no sanitizer    | critical  |\n| Authed + dangerous sink, or unauth + partial sanitization  | high      |\n| Requires specific input shape or edge case                 | medium    |\n| Theoretically reachable, requires multiple prereqs         | low       |\n\n## Anti-patterns\n\n- Reading entire files. 30–200 lines is the ceiling.\n- Emitting more than one `VULNERABILITY` per (file, function, sink).\n- Running scanner tools (\"let me re-scan this area\"). Not your job.\n- Writing bash commands. You do not have bash.\n","# Detector Skill\n\nYou promote scanner candidates into real `VULNERABILITY` nodes — or\nreject them as false positives — by reading the surrounding source.\nYou have no bash and no scanner tools. Only graph CRUD and source reads.\n\n## Per-candidate decision flow\n\n1. Pull candidate: `kg_query(kind=\"candidate\", limit=20)`.\n2. For each candidate (highest score first):\n   a. Read ±30 lines around `path:line`. Prefer function boundaries.\n   b. Identify: source? sink? taint path? sanitizer?\n   c. Load the relevant playbook: `\u002Fskills\u002Fstandard\u002Fanalyst\u002F\u003Cvuln-class>\u002FSKILL.md`.\n      Available classes: sql-injection, ssrf, deserialization, idor, ssti,\n      xss, xxe, path-traversal, command-injection, prototype-pollution,\n      prompt-injection, auth-bypass.\n   d. Decide: promote, reject, or hypothesis-only.\n3. Emit.\n\n## Promotion template\n\n```python\nvuln = kg_add_node(\n    \"vulnerability\",\n    \"SQLi in product search\",\n    props='{\"key\":\"app.py:search_products:sqli\",\"severity\":\"high\",'\n          '\"file\":\"\u002Fworkspace\u002Ftarget\u002Fapp.py\",\"line\":142,\"cwe\":[\"CWE-89\"],'\n          '\"source\":\"request.args.get(\\\\\"q\\\\\")\",\"sink\":\"cursor.execute\",'\n          '\"evidence\":\"cursor.execute(f\\\\\"SELECT * FROM products WHERE name LIKE \\'%{q}%\\'\\\\\")\"}',\n)\nhyp = kg_add_node(\n    \"hypothesis\",\n    \"Unsanitized query param flows into f-string SQL\",\n    props='{\"key\":\"app.py:search_products:sqli:hyp\"}',\n)\nkg_add_edge(vuln_id, candidate_id, \"derived_from\")\nkg_add_edge(hyp_id, vuln_id, \"mapped_to\")\n```\n\n## Rejection template\n\nSame `kg_add_node` call with the SAME `key`, plus `status=\"rejected\"`\nand `reason=\"sanitized via html.escape before sink\"`. Idempotent — the\ngraph upsert merges the rejection on top of the original candidate.\n\n## Severity calibration\n\n| Signal                                                     | Severity  |\n|------------------------------------------------------------|-----------|\n| Unauth + external input + dangerous sink + no sanitizer    | critical  |\n| Authed + dangerous sink, or unauth + partial sanitization  | high      |\n| Requires specific input shape or edge case                 | medium    |\n| Theoretically reachable, requires multiple prereqs         | low       |\n\n## Anti-patterns\n\n- Reading entire files. 30–200 lines is the ceiling.\n- Emitting more than one `VULNERABILITY` per (file, function, sink).\n- Running scanner tools (\"let me re-scan this area\"). Not your job.\n- Writing bash commands. You do not have bash.\n",{"name":5,"metadata":24,"description":7},{"subdomain":25,"when_to_use":26,"upstream_ref":27},"orchestration","detector stage 2 vulnerability candidate vulnerability hypothesis read-only source-read pipeline","Decepticon vulnresearch pipeline — stage 2 detector role","main","c0c483827a963764d5e1a663a9591867d47289e6","stack\u002Fdecepticon-slim\u002Fupstream\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fplugins\u002Fdetector","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 detector-overview",{"tool":40,"command":41},"bunx","bunx skills add Iwakishirokoshu\u002FHermesUltimate --skill detector-overview",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Iwakishirokoshu\u002FHermesUltimate --skill detector-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\u002Fdetector\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",[],[]]