[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M797PMJD2F63T0R6SB3HYPCR":3,"skill-same:01M797PMJD2F63T0R6SB3HYPCR":51},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":36,"install":37,"resources":50},"01M797PMJD2F63T0R6SB3HYPCR","finding-protocol",null,"Operational-tier finding template — minimal fields for sub-agent decision support. Heavyweight deliverable promotion lives in skills\u002Fdecepticon\u002Ffinal-report.","7ShIkI3\u002FDecepticon-x-DarkTriad","7ShIkI3","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F78133376?v=4","01M797CTK5AHH2161YVG93NJ3B","Raphael Pascaud","01M797CTKRQS64R01J7E6TJSEM",3,"Apache-2.0","https:\u002F\u002Fgithub.com\u002F7ShIkI3\u002FDecepticon-x-DarkTriad\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fshared\u002Ffinding-protocol\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: finding-protocol\ndescription: \"Operational-tier finding template — minimal fields for sub-agent decision support. Heavyweight deliverable promotion lives in skills\u002Fdecepticon\u002Ffinal-report.\"\nallowed-tools: Read Write\nmetadata:\n  subdomain: reporting\n  when_to_use: \"write finding, record finding, create finding, document vulnerability, FIND-, findings\u002F, severity\"\n  tags: finding, protocol, template, severity, reporting, documentation, operational\n  upstream_ref: \"Operational-tier finding template — sub-agent decision support output, not an attack technique\"\n---\n\n# Finding Protocol — Operational Tier\n\nThe operational tier captures the minimum information another agent (or\nthe orchestrator) needs to make a decision. It is not the report\ndeliverable — the deliverable is generated at engagement end by the\norchestrator from operational findings + attack-path narrative (see\n`skills\u002Fdecepticon\u002Ffinal-report\u002FSKILL.md`).\n\n## File Naming Convention\n\n`findings\u002FFIND-{NNN}.md`\n\nThe file name and the `id` field in YAML frontmatter (FIND-001,\nFIND-002, ...) use the same canonical cross-reference. Determine the\nnext ID by counting existing files: `ls findings\u002F*.md | wc -l`.\n\nDo not create empty scaffold directories or placeholder files before\nthere is a real artifact to write.\n\n## Operational Template\n\nEvery operational finding uses this minimal Markdown structure with\nYAML frontmatter — required fields only:\n\n```markdown\n---\nid: FIND-001\nseverity: critical\ntitle: \u003Cone-line summary>\ncwe: CWE-89               # optional at operational tier; REQUIRED at deliverable promotion\nvrt: server-side-injection\u002Fsql-injection\u002Fblind   # optional Bugcrowd VRT path (category\u002Fsub-category\u002Fvariant)\nagent: recon | exploit | postexploit | analyst | ...\nobjective_id: OBJ-001\ndiscovered_at: \"2026-04-06T14:23:11Z\"\nevidence_pointer: findings\u002Fevidence\u002FFIND-001_\u003Cslug>.txt\n---\n\n## Description\n2-4 sentences: what the issue is and where.\n\n## Evidence\n- \u003Cpointer 1>: \u003Cone-line per pointer>\n- \u003Cpointer 2>: \u003Cone-line per pointer>\n\n## Next\nnext agent should: \u003Caction>\nOR\nblocking — \u003Creason>\n```\n\nThe `## Next` section is the decision-support hook — the orchestrator\nreads it to choose the next dispatch.\n\n## Severity Guide (operational, principle-only)\n\n- **CRITICAL**: Immediate exploitation, data breach, full compromise\n- **HIGH**: Known CVE, significant misconfiguration, privilege escalation\n- **MEDIUM**: Information disclosure, weak configuration\n- **LOW**: Hardening recommendation, informational\n- **INFORMATIONAL**: Observation, no direct security impact\n\nCVSS-numeric ranges live in deliverable tier (see final-report skill). When a\nCVSS score is recorded, always store the **vector string** (CVSS v4.0, e.g.\n`CVSS:4.0\u002FAV:N\u002FAC:L\u002F...`) alongside the numeric score — the vector encodes the\nversion and makes the score reproducible\u002Fauditable (per FIRST CVSS v4.0). A\nbare number is ambiguous between v3.1 and v4.0.\n\n## Classification fields (CWE + VRT)\n\n- `cwe` — the CWE identifier (e.g. `CWE-89`). Optional at operational tier\n  (recon often cannot determine it; exploit usually can), **required** when the\n  finding is promoted to the deliverable tier.\n- `vrt` — Bugcrowd Vulnerability Rating Taxonomy path\n  `category\u002Fsub-category\u002Fvariant` (e.g. `server-side-injection\u002Fsql-injection\u002Fblind`).\n  Optional but recommended; it carries a machine-readable cross-walk to CVSS\u002FCWE\n  and a P1–P5 priority, and keeps classifications interoperable with bug-bounty\n  triage. See the VRT at github.com\u002Fbugcrowd\u002Fvulnerability-rating-taxonomy.\n\n## After Creating a Finding\n\n1. Save raw evidence to `findings\u002Fevidence\u002FFIND-{NNN}_{description}.txt`\n   only when it supports the finding.\n2. Append a timeline entry to `timeline.jsonl` for the real finding event:\n   `{\"ts\":\"...\",\"type\":\"finding\",\"id\":\"FIND-001\",\"severity\":\"critical\",\"agent\":\"recon\",\"objective\":\"OBJ-001\"}`\n\n## Rules\n\n- One Markdown file per finding — do NOT bundle multiple vulnerabilities\n- ALL agent documents use Markdown format — never write JSON as a deliverable document\n- Do NOT create `findings.md`; each finding lives in its own `findings\u002FFIND-{NNN}.md` file\n\n## Promotion to Deliverable Tier\n\nWhen the orchestrator runs the final-report skill at engagement end,\noperational findings are promoted to deliverable-tier finding documents under\n`report\u002F` with the heavyweight schema (CVSS score + vector, CWE, VRT, MITRE,\naffected_target, affected_component, confidence, phase, detected,\nremediation_priority, plus full body sections). See\n`skills\u002Fdecepticon\u002Ffinal-report\u002FSKILL.md` for the deliverable template.\n\n**Two-tier naming — the key vs. the deliverable:**\n\n- **Operational tier** (`findings\u002FFIND-{NNN}.md`) keeps the *stable*\n  `FIND-NNN` key for the whole engagement. Severity and title may change as the\n  exploit confirms impact, but the filename never does — so every cross-\n  reference (`shells.json` \u002F `creds` `finding_id`, `attack-paths\u002FPATH-NNN`\n  `finding_ids`, `timeline.jsonl`, `evidence\u002FFIND-NNN_*.txt`) stays intact.\n- **Deliverable tier** (`report\u002F\u003Cseverity>\u003CNN>-\u003Cslug>.md`) is the terminal\n  snapshot generated once at engagement end, when severity is final. It uses a\n  human-readable, severity-sorted name — e.g. `report\u002Fcritical01-struts-rce.md`,\n  `report\u002Fhigh01-git-config-disclosure.md`. The `\u003CNN>` is a per-severity\n  counter (`critical01`, `critical02`, `high01`, …) so a plain `ls report\u002F`\n  lists findings worst-first. The frontmatter still carries `id: FIND-NNN`, so\n  the readable deliverable remains traceable back to its operational finding and\n  to the attack-path \u002F shell \u002F credential cross-references.\n","# Finding Protocol — Operational Tier\n\nThe operational tier captures the minimum information another agent (or\nthe orchestrator) needs to make a decision. It is not the report\ndeliverable — the deliverable is generated at engagement end by the\norchestrator from operational findings + attack-path narrative (see\n`skills\u002Fdecepticon\u002Ffinal-report\u002FSKILL.md`).\n\n## File Naming Convention\n\n`findings\u002FFIND-{NNN}.md`\n\nThe file name and the `id` field in YAML frontmatter (FIND-001,\nFIND-002, ...) use the same canonical cross-reference. Determine the\nnext ID by counting existing files: `ls findings\u002F*.md | wc -l`.\n\nDo not create empty scaffold directories or placeholder files before\nthere is a real artifact to write.\n\n## Operational Template\n\nEvery operational finding uses this minimal Markdown structure with\nYAML frontmatter — required fields only:\n\n```markdown\n---\nid: FIND-001\nseverity: critical\ntitle: \u003Cone-line summary>\ncwe: CWE-89               # optional at operational tier; REQUIRED at deliverable promotion\nvrt: server-side-injection\u002Fsql-injection\u002Fblind   # optional Bugcrowd VRT path (category\u002Fsub-category\u002Fvariant)\nagent: recon | exploit | postexploit | analyst | ...\nobjective_id: OBJ-001\ndiscovered_at: \"2026-04-06T14:23:11Z\"\nevidence_pointer: findings\u002Fevidence\u002FFIND-001_\u003Cslug>.txt\n---\n\n## Description\n2-4 sentences: what the issue is and where.\n\n## Evidence\n- \u003Cpointer 1>: \u003Cone-line per pointer>\n- \u003Cpointer 2>: \u003Cone-line per pointer>\n\n## Next\nnext agent should: \u003Caction>\nOR\nblocking — \u003Creason>\n```\n\nThe `## Next` section is the decision-support hook — the orchestrator\nreads it to choose the next dispatch.\n\n## Severity Guide (operational, principle-only)\n\n- **CRITICAL**: Immediate exploitation, data breach, full compromise\n- **HIGH**: Known CVE, significant misconfiguration, privilege escalation\n- **MEDIUM**: Information disclosure, weak configuration\n- **LOW**: Hardening recommendation, informational\n- **INFORMATIONAL**: Observation, no direct security impact\n\nCVSS-numeric ranges live in deliverable tier (see final-report skill). When a\nCVSS score is recorded, always store the **vector string** (CVSS v4.0, e.g.\n`CVSS:4.0\u002FAV:N\u002FAC:L\u002F...`) alongside the numeric score — the vector encodes the\nversion and makes the score reproducible\u002Fauditable (per FIRST CVSS v4.0). A\nbare number is ambiguous between v3.1 and v4.0.\n\n## Classification fields (CWE + VRT)\n\n- `cwe` — the CWE identifier (e.g. `CWE-89`). Optional at operational tier\n  (recon often cannot determine it; exploit usually can), **required** when the\n  finding is promoted to the deliverable tier.\n- `vrt` — Bugcrowd Vulnerability Rating Taxonomy path\n  `category\u002Fsub-category\u002Fvariant` (e.g. `server-side-injection\u002Fsql-injection\u002Fblind`).\n  Optional but recommended; it carries a machine-readable cross-walk to CVSS\u002FCWE\n  and a P1–P5 priority, and keeps classifications interoperable with bug-bounty\n  triage. See the VRT at github.com\u002Fbugcrowd\u002Fvulnerability-rating-taxonomy.\n\n## After Creating a Finding\n\n1. Save raw evidence to `findings\u002Fevidence\u002FFIND-{NNN}_{description}.txt`\n   only when it supports the finding.\n2. Append a timeline entry to `timeline.jsonl` for the real finding event:\n   `{\"ts\":\"...\",\"type\":\"finding\",\"id\":\"FIND-001\",\"severity\":\"critical\",\"agent\":\"recon\",\"objective\":\"OBJ-001\"}`\n\n## Rules\n\n- One Markdown file per finding — do NOT bundle multiple vulnerabilities\n- ALL agent documents use Markdown format — never write JSON as a deliverable document\n- Do NOT create `findings.md`; each finding lives in its own `findings\u002FFIND-{NNN}.md` file\n\n## Promotion to Deliverable Tier\n\nWhen the orchestrator runs the final-report skill at engagement end,\noperational findings are promoted to deliverable-tier finding documents under\n`report\u002F` with the heavyweight schema (CVSS score + vector, CWE, VRT, MITRE,\naffected_target, affected_component, confidence, phase, detected,\nremediation_priority, plus full body sections). See\n`skills\u002Fdecepticon\u002Ffinal-report\u002FSKILL.md` for the deliverable template.\n\n**Two-tier naming — the key vs. the deliverable:**\n\n- **Operational tier** (`findings\u002FFIND-{NNN}.md`) keeps the *stable*\n  `FIND-NNN` key for the whole engagement. Severity and title may change as the\n  exploit confirms impact, but the filename never does — so every cross-\n  reference (`shells.json` \u002F `creds` `finding_id`, `attack-paths\u002FPATH-NNN`\n  `finding_ids`, `timeline.jsonl`, `evidence\u002FFIND-NNN_*.txt`) stays intact.\n- **Deliverable tier** (`report\u002F\u003Cseverity>\u003CNN>-\u003Cslug>.md`) is the terminal\n  snapshot generated once at engagement end, when severity is final. It uses a\n  human-readable, severity-sorted name — e.g. `report\u002Fcritical01-struts-rce.md`,\n  `report\u002Fhigh01-git-config-disclosure.md`. The `\u003CNN>` is a per-severity\n  counter (`critical01`, `critical02`, `high01`, …) so a plain `ls report\u002F`\n  lists findings worst-first. The frontmatter still carries `id: FIND-NNN`, so\n  the readable deliverable remains traceable back to its operational finding and\n  to the attack-path \u002F shell \u002F credential cross-references.\n",{"name":5,"metadata":24,"description":7,"allowed-tools":29},{"tags":25,"subdomain":26,"when_to_use":27,"upstream_ref":28},"finding, protocol, template, severity, reporting, documentation, operational","reporting","write finding, record finding, create finding, document vulnerability, FIND-, findings\u002F, severity","Operational-tier finding template — sub-agent decision support output, not an attack technique","Read Write","main","42b918525fb79065e730da3da997bffb33fcd414","packages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fshared\u002Ffinding-protocol",0,"https:\u002F\u002Fgithub.com\u002F7ShIkI3\u002FDecepticon-x-DarkTriad","https:\u002F\u002Fgithub.com\u002F7ShIkI3","2026-07-22 19:02:27",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add 7ShIkI3\u002FDecepticon-x-DarkTriad --skill finding-protocol",{"tool":43,"command":44},"bunx","bunx skills add 7ShIkI3\u002FDecepticon-x-DarkTriad --skill finding-protocol",{"tool":46,"command":47},"pnpm","pnpm dlx skills add 7ShIkI3\u002FDecepticon-x-DarkTriad --skill finding-protocol","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002F7ShIkI3\u002FDecepticon-x-DarkTriad\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fshared\u002Ffinding-protocol\u002FSKILL.md",true,[],[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":19},"01M798TNHEBA4Y67TJJ7W0KBDD","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\u002F7ShIkI3\u002FDecepticon-x-DarkTriad\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fwps-pixie-dust\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M798TH79VR8XM7AAMG0ZKSXX","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\u002F7ShIkI3\u002FDecepticon-x-DarkTriad\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fwpa3-sae\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M798TD0E10ZHQN5X362M4HG9","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\u002F7ShIkI3\u002FDecepticon-x-DarkTriad\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fwpa2-psk\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M798T7HFR3NB9WJTK1FESVF9","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\u002F7ShIkI3\u002FDecepticon-x-DarkTriad\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fwpa-enterprise-eap\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M798T38B4SV0T87VQK56KPHC","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\u002F7ShIkI3\u002FDecepticon-x-DarkTriad\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fkrack-fragattacks\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M798SXTNF0RP1DXKQEWFVQ9H","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\u002F7ShIkI3\u002FDecepticon-x-DarkTriad\u002Fblob\u002Fmain\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fwireless\u002Fevil-twin-karma\u002FSKILL.md",[],[]]