[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CMFJGAFWH27RWAQX5VNNST":3,"skill-same:01M6CMFJGAFWH27RWAQX5VNNST":85},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":46,"repositoryHtmlUrl":47,"repositoryHomepageUrl":6,"ownerHtmlUrl":48,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":49,"install":50,"resources":62},"01M6CMFJGAFWH27RWAQX5VNNST","openclaw-egress-pro",null,"Full network DLP suite: detect outbound URLs, data exfiltration patterns, and suspicious network calls, then automatically block connections, quarantine compromised skills, and enforce domain allowlists. Everything in openclaw-egress (free) plus automated countermeasures.","kbarbel640-del\u002Fskills","kbarbel640-del","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F255315490?v=4","01M6CJPPQGCCESXMG3K7BBGQ5J","01M6CJPPX2PB2BCZERFVM2C2B3",1,"MIT","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fatlaspa\u002Fopenclaw-egress-pro\u002FSKILL.md",[],[18,19,20,21,22,23,24,25,26,27,28,29],"openclaw","openclaw egress pro","suspicious","linux","win32","exfiltration","network","data","dlp","python3","patterns","connections","2026-11-10 10:12:30",false,"---\nname: openclaw-egress-pro\ndescription: \"Full network DLP suite: detect outbound URLs, data exfiltration patterns, and suspicious network calls, then automatically block connections, quarantine compromised skills, and enforce domain allowlists. Everything in openclaw-egress (free) plus automated countermeasures.\"\nuser-invocable: true\nmetadata: {\"openclaw\":{\"emoji\":\"?\",\"requires\":{\"bins\":[\"python3\"]},\"os\":[\"darwin\",\"linux\",\"win32\"]}}\n---\n\n# OpenClaw Egress Pro\n\nFull network DLP suite for agent workspaces. Detects outbound URLs, data exfiltration patterns, and suspicious network calls, then automatically blocks connections, quarantines compromised skills, and enforces domain allowlists.\n\n**Philosophy:** alert -> subvert -> quarantine -> defend.\n\nEverything in [openclaw-egress](https:\u002F\u002Fgithub.com\u002FAtlasPA\u002Fopenclaw-egress) (free) plus automated countermeasures.\n\n## The Problem\n\nSkills can phone home. A compromised skill can POST your workspace contents, API keys, or conversation history to an external server. Detection alone isn't enough — you need the ability to neutralize threats automatically.\n\n## Commands\n\n### Full Scan\n\nScan workspace for all outbound network risks.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fegress.py scan --workspace \u002Fpath\u002Fto\u002Fworkspace\n```\n\n### Skills-Only Scan\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fegress.py scan --skills-only --workspace \u002Fpath\u002Fto\u002Fworkspace\n```\n\n### Domain Map\n\nList all external domains referenced in workspace.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fegress.py domains --workspace \u002Fpath\u002Fto\u002Fworkspace\n```\n\n### Quick Status\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fegress.py status --workspace \u002Fpath\u002Fto\u002Fworkspace\n```\n\n## Pro Countermeasures\n\n### Block Network Calls\n\nNeutralize suspicious network calls in a skill by commenting them out. Targets CRITICAL and HIGH findings only. Creates `.bak` backup of each modified file.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fegress.py block \u003Cskill-name> --workspace \u002Fpath\u002Fto\u002Fworkspace\n```\n\n- Comments out lines containing network calls with `# [BLOCKED by openclaw-egress-pro]`\n- Creates `.bak` backup before modifying any file\n- Only modifies code files (`.py`, `.js`, `.ts`, `.sh`, `.bash`)\n- Flags non-code files for manual review\n\n### Quarantine Skill\n\nDisable a skill with exfiltration indicators by renaming it so OpenClaw won't load it.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fegress.py quarantine \u003Cskill-name> --workspace \u002Fpath\u002Fto\u002Fworkspace\n```\n\n### Unquarantine Skill\n\nRestore a previously quarantined skill.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fegress.py unquarantine \u003Cskill-name> --workspace \u002Fpath\u002Fto\u002Fworkspace\n```\n\n### Domain Allowlist\n\nManage a custom domain allowlist. Domains on this list won't be flagged during scans. Built-in safe domains always apply.\n\n```bash\n# Show current allowlist (built-in + custom)\npython3 {baseDir}\u002Fscripts\u002Fegress.py allowlist --workspace \u002Fpath\u002Fto\u002Fworkspace\n\n# Add a domain\npython3 {baseDir}\u002Fscripts\u002Fegress.py allowlist --add api.mycompany.com --workspace \u002Fpath\u002Fto\u002Fworkspace\n\n# Remove a domain\npython3 {baseDir}\u002Fscripts\u002Fegress.py allowlist --remove api.mycompany.com --workspace \u002Fpath\u002Fto\u002Fworkspace\n```\n\nCustom allowlist is stored in `.egress-allowlist.json` in the workspace root.\n\n### Protect (Full Sweep)\n\nAutomated protection sweep: scans all skills, auto-quarantines any with CRITICAL exfiltration indicators, blocks HIGH network calls, and reports results. Recommended for session startup.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fegress.py protect --workspace \u002Fpath\u002Fto\u002Fworkspace\n```\n\nActions taken by protect:\n1. Scan all active (non-quarantined) skills\n2. **CRITICAL findings** -> quarantine the entire skill\n3. **HIGH findings** -> block (comment out) network call lines\n4. Report all actions taken with next steps\n\n## What It Detects\n\n| Risk | Pattern |\n|------|---------|\n| **CRITICAL** | Base64\u002Fhex payloads in URLs, pastebin\u002Fsharing services, request catchers, dynamic DNS |\n| **HIGH** | Network function calls (requests, urllib, curl, wget, fetch), webhook\u002Fcallback URLs |\n| **WARNING** | Suspicious TLDs (.xyz, .tk, .ml), URL shorteners, IP address endpoints |\n| **INFO** | Any external URL not on the safe domain list or custom allowlist |\n\n## Exit Codes\n\n- `0` — Clean (or action completed successfully)\n- `1` — Warnings \u002F network calls detected (review needed)\n- `2` — Critical exfiltration risk detected (action needed)\n\n## No External Dependencies\n\nPython standard library only. No pip install. No network calls. Everything runs locally.\n\n## Cross-Platform\n\nWorks with OpenClaw, Claude Code, Cursor, and any tool using the Agent Skills specification.\n","# OpenClaw Egress Pro\n\nFull network DLP suite for agent workspaces. Detects outbound URLs, data exfiltration patterns, and suspicious network calls, then automatically blocks connections, quarantines compromised skills, and enforces domain allowlists.\n\n**Philosophy:** alert -> subvert -> quarantine -> defend.\n\nEverything in [openclaw-egress](https:\u002F\u002Fgithub.com\u002FAtlasPA\u002Fopenclaw-egress) (free) plus automated countermeasures.\n\n## The Problem\n\nSkills can phone home. A compromised skill can POST your workspace contents, API keys, or conversation history to an external server. Detection alone isn't enough — you need the ability to neutralize threats automatically.\n\n## Commands\n\n### Full Scan\n\nScan workspace for all outbound network risks.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fegress.py scan --workspace \u002Fpath\u002Fto\u002Fworkspace\n```\n\n### Skills-Only Scan\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fegress.py scan --skills-only --workspace \u002Fpath\u002Fto\u002Fworkspace\n```\n\n### Domain Map\n\nList all external domains referenced in workspace.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fegress.py domains --workspace \u002Fpath\u002Fto\u002Fworkspace\n```\n\n### Quick Status\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fegress.py status --workspace \u002Fpath\u002Fto\u002Fworkspace\n```\n\n## Pro Countermeasures\n\n### Block Network Calls\n\nNeutralize suspicious network calls in a skill by commenting them out. Targets CRITICAL and HIGH findings only. Creates `.bak` backup of each modified file.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fegress.py block \u003Cskill-name> --workspace \u002Fpath\u002Fto\u002Fworkspace\n```\n\n- Comments out lines containing network calls with `# [BLOCKED by openclaw-egress-pro]`\n- Creates `.bak` backup before modifying any file\n- Only modifies code files (`.py`, `.js`, `.ts`, `.sh`, `.bash`)\n- Flags non-code files for manual review\n\n### Quarantine Skill\n\nDisable a skill with exfiltration indicators by renaming it so OpenClaw won't load it.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fegress.py quarantine \u003Cskill-name> --workspace \u002Fpath\u002Fto\u002Fworkspace\n```\n\n### Unquarantine Skill\n\nRestore a previously quarantined skill.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fegress.py unquarantine \u003Cskill-name> --workspace \u002Fpath\u002Fto\u002Fworkspace\n```\n\n### Domain Allowlist\n\nManage a custom domain allowlist. Domains on this list won't be flagged during scans. Built-in safe domains always apply.\n\n```bash\n# Show current allowlist (built-in + custom)\npython3 {baseDir}\u002Fscripts\u002Fegress.py allowlist --workspace \u002Fpath\u002Fto\u002Fworkspace\n\n# Add a domain\npython3 {baseDir}\u002Fscripts\u002Fegress.py allowlist --add api.mycompany.com --workspace \u002Fpath\u002Fto\u002Fworkspace\n\n# Remove a domain\npython3 {baseDir}\u002Fscripts\u002Fegress.py allowlist --remove api.mycompany.com --workspace \u002Fpath\u002Fto\u002Fworkspace\n```\n\nCustom allowlist is stored in `.egress-allowlist.json` in the workspace root.\n\n### Protect (Full Sweep)\n\nAutomated protection sweep: scans all skills, auto-quarantines any with CRITICAL exfiltration indicators, blocks HIGH network calls, and reports results. Recommended for session startup.\n\n```bash\npython3 {baseDir}\u002Fscripts\u002Fegress.py protect --workspace \u002Fpath\u002Fto\u002Fworkspace\n```\n\nActions taken by protect:\n1. Scan all active (non-quarantined) skills\n2. **CRITICAL findings** -> quarantine the entire skill\n3. **HIGH findings** -> block (comment out) network call lines\n4. Report all actions taken with next steps\n\n## What It Detects\n\n| Risk | Pattern |\n|------|---------|\n| **CRITICAL** | Base64\u002Fhex payloads in URLs, pastebin\u002Fsharing services, request catchers, dynamic DNS |\n| **HIGH** | Network function calls (requests, urllib, curl, wget, fetch), webhook\u002Fcallback URLs |\n| **WARNING** | Suspicious TLDs (.xyz, .tk, .ml), URL shorteners, IP address endpoints |\n| **INFO** | Any external URL not on the safe domain list or custom allowlist |\n\n## Exit Codes\n\n- `0` — Clean (or action completed successfully)\n- `1` — Warnings \u002F network calls detected (review needed)\n- `2` — Critical exfiltration risk detected (action needed)\n\n## No External Dependencies\n\nPython standard library only. No pip install. No network calls. Everything runs locally.\n\n## Cross-Platform\n\nWorks with OpenClaw, Claude Code, Cursor, and any tool using the Agent Skills specification.\n",{"name":5,"metadata":35,"description":7,"user-invocable":42},{"openclaw":36},{"os":37,"emoji":39,"requires":40},[38,21,22],"darwin","?",{"bins":41},[27],true,"main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Fatlaspa\u002Fopenclaw-egress-pro",0,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del","2026-08-23 22:39:37",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":42},[52,55,58],{"tool":53,"command":54},"npx","npx skills add kbarbel640-del\u002Fskills --skill openclaw-egress-pro",{"tool":56,"command":57},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill openclaw-egress-pro",{"tool":59,"command":60},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill openclaw-egress-pro","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fatlaspa\u002Fopenclaw-egress-pro\u002FSKILL.md",[63,69,73,79],{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"_meta.json","REFERENCE","参考文档",291,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fatlaspa\u002Fopenclaw-egress-pro\u002F_meta.json",{"path":70,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":71,"sourceHtmlUrl":72},"README.md",2513,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fatlaspa\u002Fopenclaw-egress-pro\u002FREADME.md",{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"scripts\u002Fegress.py","SCRIPT","脚本",24157,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fatlaspa\u002Fopenclaw-egress-pro\u002Fscripts\u002Fegress.py",{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"SKILL.md.tmpl","OTHER","其他",44096,"https:\u002F\u002Fgithub.com\u002Fendman100\u002Fskill-router-nexus\u002Fblob\u002Fmain\u002FCI-CD-and-Monitoring\u002Fgstack-land-and-deploy\u002Fland-and-deploy\u002FSKILL.md.tmpl",[86,117,145,166,172,190],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":97,"publishedAt":30},"01M6G8J55967D6281ACMKAKTEQ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[92],{"categoryNo":93,"categoryName":94,"taxonomyType":95,"taxonomyTypeDesc":96},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116],"crowd prompting","prompting","api","with","tokens","domain","world","prompts","operations","instructions","text","tool","system","improve","productivity","marketplace","https","content","ai agents",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":128,"publishedAt":30},"01M6G8J0PKPAYVET6BWE8W4C26","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[123],{"categoryNo":124,"categoryName":125,"taxonomyType":126,"taxonomyTypeDesc":127},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[129,100,130,131,132,133,134,135,136,137,18,138,139,140,141,142,143,105,144],"dilemm ai","arena","analyze","browser","openclaw agent","create","automation","browser automation","bot","design","strategy","headless","compete","submit","matchmaking","use",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":154,"publishedAt":30},"01M6G8HWAF3K9SW7NP3Z83CPJ6","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, and submit comments. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, or submitting paper reviews via API at http:\u002F\u002F150.158.152.82:8000.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Fweak-accept\u002FSKILL.md",[151],{"categoryNo":152,"categoryName":153,"taxonomyType":126,"taxonomyTypeDesc":127},"01JBSEEDCAT000000000000021","资料检索与研究",[155,156,157,158,159,160,161,101,162,142,144,163,100,164,165],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","read","http","via",{"skillNo":167,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":171,"publishedAt":30},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[170],{"categoryNo":152,"categoryName":153,"taxonomyType":126,"taxonomyTypeDesc":127},[158,157,156,155,165,160,161,101,159,142,144,162,163,100,164],{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":178,"publishedAt":30},"01M6G8HM95Y64JNVFC2HN4E2BG","git-summary","Get a quick summary of the current Git repository including status, recent commits, branches, and contributors.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzweack\u002Fgit-summary\u002FSKILL.md",[],[179,180,181,182,183,22,184,21,185,186,187,188,189],"git","summary","git summary","commits","repository","status","contributors","true","quick","get","branches",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":200,"publishedAt":30},"01M6G8HGEGF05CNEJCGVYFSC4R","agent-constitution","Interact with AgentConstitution governance contracts on Base Sepolia. Check compliance, read rules, log actions, query governance state.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fztsalexey\u002Fagent-constitution\u002FSKILL.md",[196,197],{"categoryNo":124,"categoryName":125,"taxonomyType":126,"taxonomyTypeDesc":127},{"categoryNo":198,"categoryName":199,"taxonomyType":95,"taxonomyTypeDesc":96},"01JBSEEDCAT000000000000037","律师与法务",[201,202,203,204,101,205,206,43,207,163,208,209,210,211,212,114,213,214,215],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]