[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77064NTYGHDKMJEMAJTM5M9":3,"skill-same:01M77064NTYGHDKMJEMAJTM5M9":50},{"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":14,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M77064NTYGHDKMJEMAJTM5M9","pentest-task-tree",null,"Iterative PTT (Penetration Testing Tree) session reasoning — build, update, and traverse a live numbered task tree to drive LLM-guided pentest decisions across a full session.","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\u002Fstandard\u002Fdecepticon\u002Fpentest-task-tree\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: pentest-task-tree\ndescription: \"Iterative PTT (Penetration Testing Tree) session reasoning — build, update, and traverse a live numbered task tree to drive LLM-guided pentest decisions across a full session.\"\nallowed-tools: Bash Read Write\nmetadata:\n  subdomain: orchestration\n  when_to_use: \"PTT, task tree, what to do next, next task, session reasoning, iterative pentest, live pentest session, update task list, pentest tree, task selection\"\n  tags: ptt, task-tree, session-reasoning, iterative, decision-making, llm-pentest, pentestgpt\n  upstream_ref: \"PentestGPT (Gelei Deng et al., USENIX Security 2024) — pentest task tree methodology spanning the full ATT&CK Enterprise kill chain\"\n---\n\n# Pentest Task Tree (PTT) — Session Reasoning Playbook\n\n> **Authorized use only.** This methodology is for certified penetration testers operating under a signed scope-of-work, rules of engagement (RoE), and explicit written authorization. Do not apply to systems you do not own or have written permission to test.\n\n## What This Skill Does\n\nThe PTT methodology converts a live pentest into a session-stateful, LLM-reasoned task graph. Unlike static checklists, the PTT starts minimal, expands only on discovered evidence, and always exposes a single ranked \"next node\" to execute — preventing scope creep, cognitive overload, and wasted effort on unconfirmed attack surfaces.\n\nThis skill is the live-session reasoning complement to `orchestration` (multi-agent delegation) and `kill-chain-analysis` (post-recon vector scoring). Use it when you want a single operator driving a session with a maintained task tree rather than delegating to sub-agents.\n\n---\n\n## PTT Format\n\n```\n1. Reconnaissance                              [to-do]\n   1.1 Passive information gathering           [completed]\n   1.2 Active port scan (nmap -sV -sC -p-)     [to-do]\n   1.3 Service fingerprinting                  [to-do]\n2. Initial Access                              [to-do]\n   2.1 Web application testing (port 80\u002F443)   [to-do]\n       2.1.1 Directory enumeration (gobuster)  [to-do]\n       2.1.2 CMS\u002Fversion identification        [to-do]\n   2.2 SSH brute-force (port 22)               [not-applicable]\n3. Privilege Escalation                        [to-do]\n```\n\n**Rules:**\n- Layer depth: `1`, `1.1`, `1.1.1` etc. Each child is a concrete sub-operation of its parent.\n- Status values: `to-do`, `completed`, `not-applicable`. Never leave a node status-less.\n- Do NOT pre-generate nodes for unknown ports\u002Fservices. Expand only on confirmed evidence.\n- Remove\u002Fprune stale or invalidated nodes aggressively to control token budget.\n- The tree is written to disk (`\u003Cengagement>\u002Fptt.md`) after every update.\n\n---\n\n## Session Lifecycle\n\n### Phase 1 — Tree Initialization\n\n**Input:** Target description (IP, URL, brief scope notes from RoE)\n\n**Action:**\n1. Generate root nodes only — typically reconnaissance tasks.\n2. Do not generate exploitation nodes until recon confirms a surface.\n3. Write initial PTT to `\u003Cengagement>\u002Fptt.md`.\n\n**Starting template:**\n```\n1. Reconnaissance                              [to-do]\n   1.1 Passive information gathering           [to-do]\n   1.2 Active port\u002Fservice scan                [to-do]\n2. (Expand after recon confirms attack surface)\n```\n\n### Phase 2 — Task Selection Loop\n\nEach iteration of the main loop:\n\n1. **Read** current PTT from `\u003Cengagement>\u002Fptt.md`.\n2. **Filter** all `to-do` leaf nodes (leaf = no children, or all children also to-do).\n3. **Score** each candidate:\n   ```\n   Priority = (P_success × Impact) \u002F Detection_risk\n   ```\n   Prefer: confirmed vulns > misconfigs > spray\u002Fbrute force > speculative nodes.\n4. **Select** the single highest-priority leaf node.\n5. **Emit** the next-task block in the canonical three-sentence format:\n   ```\n   -----\n   Task: \u003Cwhat to do — one sentence>\n   Command: \u003Cexact command or GUI steps>\n   Expected outcome: \u003Cwhat success looks like>\n   ```\n6. Execute (or hand to operator), then proceed to Phase 3.\n\n### Phase 3 — Result Ingestion and Tree Update\n\n**Input processing (parse before reasoning):**\n\nRaw tool output is noisy. Before updating the PTT, distill the output:\n\n| Input type | Distillation rule |\n|---|---|\n| `nmap` output | Keep: open ports, service\u002Fversion, script results. Drop: closed\u002Ffiltered noise. |\n| Web page \u002F Burp response | Keep: forms, parameters, comments, error messages, auth state. Drop: boilerplate HTML. |\n| `gobuster` \u002F `ffuf` | Keep: non-404 paths, redirect targets, interesting status codes (200\u002F301\u002F403\u002F500). |\n| `nikto` output | Keep: CVE references, misconfig findings. Drop: informational noise. |\n| Exploit output | Keep: shell prompt, privilege level, hostname, error messages. |\n| Arbitrary operator note | Rephrase to one concise sentence preserving all field:value pairs. |\n\n**Tree update rules (apply in order):**\n1. Mark the executed node `completed` if successful, `not-applicable` if confirmed inapplicable.\n2. Add child nodes only for newly confirmed services\u002Fpaths\u002Fvulns — do not speculate.\n3. Delete nodes invalidated by findings (e.g., port closed → remove service sub-tree).\n4. If a new attack surface opens, add a new top-level or mid-level node.\n5. Write updated PTT back to `\u003Cengagement>\u002Fptt.md`.\n6. Return to Phase 2.\n\n---\n\n## Decision Logic: Which Node Next?\n\n```\nIs there a confirmed vulnerability \u002F credential \u002F shell from the last step?\n├── YES → Immediately prioritize exploitation or post-exploitation node\n│         (Do not queue more recon when you have a live lead)\n└── NO  → Continue down the recon\u002Fenumeration branch\n\nIs the current branch exhausted (all leaves completed or not-applicable)?\n├── YES → Expand to adjacent attack surface OR escalate to next kill-chain phase\n└── NO  → Stay in current branch, pick highest-scored to-do leaf\n\nAre all nodes completed or not-applicable?\n├── YES → Session complete — generate PTT summary and hand off to reporting\n└── NO  → Continue loop\n```\n\n**Hard rule:** A confirmed vuln\u002Fshell\u002Fcred overrides any pending enumeration node. Never run \"one more scan\" when exploitation is available.\n\n---\n\n## Tool-Output Distillation Examples\n\n### nmap raw → distilled\n```\n# Raw (noisy)\n22\u002Ftcp  open  ssh     OpenSSH 8.9p1 Ubuntu\n80\u002Ftcp  open  http    Apache httpd 2.4.52\n443\u002Ftcp open  ssl\u002Fhttp Apache httpd 2.4.52\n8080\u002Ftcp filtered http\n...\n(500 lines of script output)\n\n# Distilled (PTT-ready)\nPort 22: OpenSSH 8.9p1 Ubuntu (open)\nPort 80: Apache 2.4.52 HTTP (open)\nPort 443: Apache 2.4.52 HTTPS (open)\nPort 8080: filtered\n```\nExpand PTT: add `2.1 Web (80)`, `2.2 Web (443)`, mark SSH node low-priority.\n\n### gobuster raw → distilled\n```\n# Raw\n\u002Findex.php      (Status: 200) [Size: 4821]\n\u002Fadmin          (Status: 301) [Size: 312] [--> \u002Fadmin\u002F]\n\u002Fconfig.php     (Status: 403) [Size: 277]\n\u002Fbackup.zip     (Status: 200) [Size: 1048576]\n```\nDistilled: `\u002Fadmin\u002F` redirect (interesting), `\u002Fconfig.php` 403 (exists, access-controlled), `\u002Fbackup.zip` 200 (high-value download).\nExpand PTT: add nodes for `\u002Fadmin\u002F` auth bypass test, `\u002Fbackup.zip` download and analysis.\n\n---\n\n## PTT State File: `\u003Cengagement>\u002Fptt.md`\n\n```markdown\n# PTT — \u003Cengagement name>\nUpdated: \u003Ctimestamp>\n\n1. Reconnaissance                              [completed]\n   1.1 Passive information gathering           [completed]\n   1.2 Active port scan                        [completed]\n       Findings: ports 22, 80, 443 open\n   1.3 Service fingerprinting                  [completed]\n       Findings: Apache 2.4.52, OpenSSH 8.9p1\n2. Initial Access                              [to-do]\n   2.1 Web application (port 80\u002F443)           [to-do]\n       2.1.1 Directory enumeration             [completed]\n             Findings: \u002Fadmin\u002F (301), \u002Fbackup.zip (200)\n       2.1.2 \u002Fbackup.zip download + analysis   [to-do]  ← NEXT\n       2.1.3 \u002Fadmin\u002F authentication testing    [to-do]\n   2.2 SSH (port 22)                           [to-do]\n3. Privilege Escalation                        [to-do]  ← expand after foothold\n```\n\n**Next task block (emitted to operator):**\n```\n-----\nTask: Download \u002Fbackup.zip and inspect its contents for credentials, source code, or configuration files.\nCommand: wget http:\u002F\u002F\u003Ctarget>\u002Fbackup.zip -O backup.zip && unzip -l backup.zip\nExpected outcome: A file listing that reveals source code, database configs, or hardcoded credentials usable for further access.\n```\n\n---\n\n## Integration with Decepticon Skills\n\n| Situation | Companion skill |\n|---|---|\n| Need to choose between multiple confirmed attack vectors | `kill-chain-analysis` |\n| Foothold established, planning post-exploit | `post-exploit\u002Fworkflow` |\n| AD services confirmed on network | `ad\u002Fkerberoasting`, `ad\u002Fbloodhound-query` |\n| WAF\u002FEDR blocking technique | `defense-evasion` |\n| Session complete, write report | `decepticon\u002Ffinal-report` |\n| Multi-agent delegation preferred over single-session | `decepticon\u002Forchestration` |\n\n---\n\n## MITRE ATT&CK Mapping\n\n| PTT Phase | ATT&CK Tactic | Key Techniques |\n|---|---|---|\n| Reconnaissance | TA0043 | T1595 (Active Scan), T1592 (Host Info), T1589 (Identity) |\n| Initial Access | TA0001 | T1190 (Exploit Public-Facing App), T1133 (External Remote), T1566 (Phishing) |\n| Execution | TA0002 | T1059 (Command\u002FScript Interpreter), T1203 (Exploit for Client Exec) |\n| Persistence | TA0003 | T1505 (Server Software Component), T1078 (Valid Accounts) |\n| Priv Esc | TA0004 | T1068 (Exploit for Priv Esc), T1548 (Abuse Elevation Control) |\n| Defense Evasion | TA0005 | T1055 (Process Injection), T1070 (Indicator Removal) |\n| Credential Access | TA0006 | T1003 (OS Credential Dumping), T1552 (Unsecured Credentials) |\n| Discovery | TA0007 | T1082 (System Info), T1083 (File\u002FDir Discovery), T1046 (Net Service Scan) |\n| Lateral Movement | TA0008 | T1021 (Remote Services), T1550 (Use Alt Auth Material) |\n\n---\n\n## Detection Notes\n\nDefenders should monitor for:\n- Sequential port scans from a single source (TA0043 \u002F T1595)\n- Rapid HTTP 404\u002F200\u002F301 enumeration patterns (T1595.003)\n- Unusual downloads of large archive files from web roots\n- Login attempts against admin panels following enumeration\n\n---\n\n## Reference\n\nBased on the PTT (Penetration Testing Tree) framework introduced in:\n> Deng et al., \"PentestGPT: An LLM-Empowered Automatic Penetration Testing Framework\", USENIX Security 2024.\n> https:\u002F\u002Fwww.usenix.org\u002Fconference\u002Fusenixsecurity24\u002Fpresentation\u002Fdeng\n","# Pentest Task Tree (PTT) — Session Reasoning Playbook\n\n> **Authorized use only.** This methodology is for certified penetration testers operating under a signed scope-of-work, rules of engagement (RoE), and explicit written authorization. Do not apply to systems you do not own or have written permission to test.\n\n## What This Skill Does\n\nThe PTT methodology converts a live pentest into a session-stateful, LLM-reasoned task graph. Unlike static checklists, the PTT starts minimal, expands only on discovered evidence, and always exposes a single ranked \"next node\" to execute — preventing scope creep, cognitive overload, and wasted effort on unconfirmed attack surfaces.\n\nThis skill is the live-session reasoning complement to `orchestration` (multi-agent delegation) and `kill-chain-analysis` (post-recon vector scoring). Use it when you want a single operator driving a session with a maintained task tree rather than delegating to sub-agents.\n\n---\n\n## PTT Format\n\n```\n1. Reconnaissance                              [to-do]\n   1.1 Passive information gathering           [completed]\n   1.2 Active port scan (nmap -sV -sC -p-)     [to-do]\n   1.3 Service fingerprinting                  [to-do]\n2. Initial Access                              [to-do]\n   2.1 Web application testing (port 80\u002F443)   [to-do]\n       2.1.1 Directory enumeration (gobuster)  [to-do]\n       2.1.2 CMS\u002Fversion identification        [to-do]\n   2.2 SSH brute-force (port 22)               [not-applicable]\n3. Privilege Escalation                        [to-do]\n```\n\n**Rules:**\n- Layer depth: `1`, `1.1`, `1.1.1` etc. Each child is a concrete sub-operation of its parent.\n- Status values: `to-do`, `completed`, `not-applicable`. Never leave a node status-less.\n- Do NOT pre-generate nodes for unknown ports\u002Fservices. Expand only on confirmed evidence.\n- Remove\u002Fprune stale or invalidated nodes aggressively to control token budget.\n- The tree is written to disk (`\u003Cengagement>\u002Fptt.md`) after every update.\n\n---\n\n## Session Lifecycle\n\n### Phase 1 — Tree Initialization\n\n**Input:** Target description (IP, URL, brief scope notes from RoE)\n\n**Action:**\n1. Generate root nodes only — typically reconnaissance tasks.\n2. Do not generate exploitation nodes until recon confirms a surface.\n3. Write initial PTT to `\u003Cengagement>\u002Fptt.md`.\n\n**Starting template:**\n```\n1. Reconnaissance                              [to-do]\n   1.1 Passive information gathering           [to-do]\n   1.2 Active port\u002Fservice scan                [to-do]\n2. (Expand after recon confirms attack surface)\n```\n\n### Phase 2 — Task Selection Loop\n\nEach iteration of the main loop:\n\n1. **Read** current PTT from `\u003Cengagement>\u002Fptt.md`.\n2. **Filter** all `to-do` leaf nodes (leaf = no children, or all children also to-do).\n3. **Score** each candidate:\n   ```\n   Priority = (P_success × Impact) \u002F Detection_risk\n   ```\n   Prefer: confirmed vulns > misconfigs > spray\u002Fbrute force > speculative nodes.\n4. **Select** the single highest-priority leaf node.\n5. **Emit** the next-task block in the canonical three-sentence format:\n   ```\n   -----\n   Task: \u003Cwhat to do — one sentence>\n   Command: \u003Cexact command or GUI steps>\n   Expected outcome: \u003Cwhat success looks like>\n   ```\n6. Execute (or hand to operator), then proceed to Phase 3.\n\n### Phase 3 — Result Ingestion and Tree Update\n\n**Input processing (parse before reasoning):**\n\nRaw tool output is noisy. Before updating the PTT, distill the output:\n\n| Input type | Distillation rule |\n|---|---|\n| `nmap` output | Keep: open ports, service\u002Fversion, script results. Drop: closed\u002Ffiltered noise. |\n| Web page \u002F Burp response | Keep: forms, parameters, comments, error messages, auth state. Drop: boilerplate HTML. |\n| `gobuster` \u002F `ffuf` | Keep: non-404 paths, redirect targets, interesting status codes (200\u002F301\u002F403\u002F500). |\n| `nikto` output | Keep: CVE references, misconfig findings. Drop: informational noise. |\n| Exploit output | Keep: shell prompt, privilege level, hostname, error messages. |\n| Arbitrary operator note | Rephrase to one concise sentence preserving all field:value pairs. |\n\n**Tree update rules (apply in order):**\n1. Mark the executed node `completed` if successful, `not-applicable` if confirmed inapplicable.\n2. Add child nodes only for newly confirmed services\u002Fpaths\u002Fvulns — do not speculate.\n3. Delete nodes invalidated by findings (e.g., port closed → remove service sub-tree).\n4. If a new attack surface opens, add a new top-level or mid-level node.\n5. Write updated PTT back to `\u003Cengagement>\u002Fptt.md`.\n6. Return to Phase 2.\n\n---\n\n## Decision Logic: Which Node Next?\n\n```\nIs there a confirmed vulnerability \u002F credential \u002F shell from the last step?\n├── YES → Immediately prioritize exploitation or post-exploitation node\n│         (Do not queue more recon when you have a live lead)\n└── NO  → Continue down the recon\u002Fenumeration branch\n\nIs the current branch exhausted (all leaves completed or not-applicable)?\n├── YES → Expand to adjacent attack surface OR escalate to next kill-chain phase\n└── NO  → Stay in current branch, pick highest-scored to-do leaf\n\nAre all nodes completed or not-applicable?\n├── YES → Session complete — generate PTT summary and hand off to reporting\n└── NO  → Continue loop\n```\n\n**Hard rule:** A confirmed vuln\u002Fshell\u002Fcred overrides any pending enumeration node. Never run \"one more scan\" when exploitation is available.\n\n---\n\n## Tool-Output Distillation Examples\n\n### nmap raw → distilled\n```\n# Raw (noisy)\n22\u002Ftcp  open  ssh     OpenSSH 8.9p1 Ubuntu\n80\u002Ftcp  open  http    Apache httpd 2.4.52\n443\u002Ftcp open  ssl\u002Fhttp Apache httpd 2.4.52\n8080\u002Ftcp filtered http\n...\n(500 lines of script output)\n\n# Distilled (PTT-ready)\nPort 22: OpenSSH 8.9p1 Ubuntu (open)\nPort 80: Apache 2.4.52 HTTP (open)\nPort 443: Apache 2.4.52 HTTPS (open)\nPort 8080: filtered\n```\nExpand PTT: add `2.1 Web (80)`, `2.2 Web (443)`, mark SSH node low-priority.\n\n### gobuster raw → distilled\n```\n# Raw\n\u002Findex.php      (Status: 200) [Size: 4821]\n\u002Fadmin          (Status: 301) [Size: 312] [--> \u002Fadmin\u002F]\n\u002Fconfig.php     (Status: 403) [Size: 277]\n\u002Fbackup.zip     (Status: 200) [Size: 1048576]\n```\nDistilled: `\u002Fadmin\u002F` redirect (interesting), `\u002Fconfig.php` 403 (exists, access-controlled), `\u002Fbackup.zip` 200 (high-value download).\nExpand PTT: add nodes for `\u002Fadmin\u002F` auth bypass test, `\u002Fbackup.zip` download and analysis.\n\n---\n\n## PTT State File: `\u003Cengagement>\u002Fptt.md`\n\n```markdown\n# PTT — \u003Cengagement name>\nUpdated: \u003Ctimestamp>\n\n1. Reconnaissance                              [completed]\n   1.1 Passive information gathering           [completed]\n   1.2 Active port scan                        [completed]\n       Findings: ports 22, 80, 443 open\n   1.3 Service fingerprinting                  [completed]\n       Findings: Apache 2.4.52, OpenSSH 8.9p1\n2. Initial Access                              [to-do]\n   2.1 Web application (port 80\u002F443)           [to-do]\n       2.1.1 Directory enumeration             [completed]\n             Findings: \u002Fadmin\u002F (301), \u002Fbackup.zip (200)\n       2.1.2 \u002Fbackup.zip download + analysis   [to-do]  ← NEXT\n       2.1.3 \u002Fadmin\u002F authentication testing    [to-do]\n   2.2 SSH (port 22)                           [to-do]\n3. Privilege Escalation                        [to-do]  ← expand after foothold\n```\n\n**Next task block (emitted to operator):**\n```\n-----\nTask: Download \u002Fbackup.zip and inspect its contents for credentials, source code, or configuration files.\nCommand: wget http:\u002F\u002F\u003Ctarget>\u002Fbackup.zip -O backup.zip && unzip -l backup.zip\nExpected outcome: A file listing that reveals source code, database configs, or hardcoded credentials usable for further access.\n```\n\n---\n\n## Integration with Decepticon Skills\n\n| Situation | Companion skill |\n|---|---|\n| Need to choose between multiple confirmed attack vectors | `kill-chain-analysis` |\n| Foothold established, planning post-exploit | `post-exploit\u002Fworkflow` |\n| AD services confirmed on network | `ad\u002Fkerberoasting`, `ad\u002Fbloodhound-query` |\n| WAF\u002FEDR blocking technique | `defense-evasion` |\n| Session complete, write report | `decepticon\u002Ffinal-report` |\n| Multi-agent delegation preferred over single-session | `decepticon\u002Forchestration` |\n\n---\n\n## MITRE ATT&CK Mapping\n\n| PTT Phase | ATT&CK Tactic | Key Techniques |\n|---|---|---|\n| Reconnaissance | TA0043 | T1595 (Active Scan), T1592 (Host Info), T1589 (Identity) |\n| Initial Access | TA0001 | T1190 (Exploit Public-Facing App), T1133 (External Remote), T1566 (Phishing) |\n| Execution | TA0002 | T1059 (Command\u002FScript Interpreter), T1203 (Exploit for Client Exec) |\n| Persistence | TA0003 | T1505 (Server Software Component), T1078 (Valid Accounts) |\n| Priv Esc | TA0004 | T1068 (Exploit for Priv Esc), T1548 (Abuse Elevation Control) |\n| Defense Evasion | TA0005 | T1055 (Process Injection), T1070 (Indicator Removal) |\n| Credential Access | TA0006 | T1003 (OS Credential Dumping), T1552 (Unsecured Credentials) |\n| Discovery | TA0007 | T1082 (System Info), T1083 (File\u002FDir Discovery), T1046 (Net Service Scan) |\n| Lateral Movement | TA0008 | T1021 (Remote Services), T1550 (Use Alt Auth Material) |\n\n---\n\n## Detection Notes\n\nDefenders should monitor for:\n- Sequential port scans from a single source (TA0043 \u002F T1595)\n- Rapid HTTP 404\u002F200\u002F301 enumeration patterns (T1595.003)\n- Unusual downloads of large archive files from web roots\n- Login attempts against admin panels following enumeration\n\n---\n\n## Reference\n\nBased on the PTT (Penetration Testing Tree) framework introduced in:\n> Deng et al., \"PentestGPT: An LLM-Empowered Automatic Penetration Testing Framework\", USENIX Security 2024.\n> https:\u002F\u002Fwww.usenix.org\u002Fconference\u002Fusenixsecurity24\u002Fpresentation\u002Fdeng\n",{"name":5,"metadata":24,"description":7,"allowed-tools":29},{"tags":25,"subdomain":26,"when_to_use":27,"upstream_ref":28},"ptt, task-tree, session-reasoning, iterative, decision-making, llm-pentest, pentestgpt","orchestration","PTT, task tree, what to do next, next task, session reasoning, iterative pentest, live pentest session, update task list, pentest tree, task selection","PentestGPT (Gelei Deng et al., USENIX Security 2024) — pentest task tree methodology spanning the full ATT&CK Enterprise kill chain","Bash Read Write","main","c0c483827a963764d5e1a663a9591867d47289e6","stack\u002Fdecepticon-slim\u002Fupstream\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fdecepticon\u002Fpentest-task-tree","https:\u002F\u002Fgithub.com\u002FIwakishirokoshu\u002FHermesUltimate","https:\u002F\u002Fgithub.com\u002FIwakishirokoshu","2026-06-15 13:48:41",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add Iwakishirokoshu\u002FHermesUltimate --skill pentest-task-tree",{"tool":42,"command":43},"bunx","bunx skills add Iwakishirokoshu\u002FHermesUltimate --skill pentest-task-tree",{"tool":45,"command":46},"pnpm","pnpm dlx skills add Iwakishirokoshu\u002FHermesUltimate --skill pentest-task-tree","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FIwakishirokoshu\u002FHermesUltimate\u002Fblob\u002Fmain\u002Fstack\u002Fdecepticon-slim\u002Fupstream\u002Fpackages\u002Fdecepticon\u002Fdecepticon\u002Fskills\u002Fstandard\u002Fdecepticon\u002Fpentest-task-tree\u002FSKILL.md",true,[],[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"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":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"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":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"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":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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",[],[]]