[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FNETJ51TNJWSW1KRHQKXFS":3,"skill-same:01M6FNETJ51TNJWSW1KRHQKXFS":120},{"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":22,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":47,"commitSha":48,"skillDirectory":49,"forksCount":50,"repositoryHtmlUrl":51,"repositoryHomepageUrl":6,"ownerHtmlUrl":52,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":53,"install":54,"resources":67},"01M6FNETJ51TNJWSW1KRHQKXFS","senseguard",null,"Semantic security scanner for OpenClaw skills. Detects prompt injection, data exfiltration, and hidden instructions that traditional code scanners miss. Use when user asks to scan skills, check skill safety, or run a security audit.","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\u002Ffermionoid\u002Fsenseguard\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"Safety","scan","scanner","use","user","instructions","check","prompt","security audit","openclaw","injection","data","exfiltration","audit","code","run","security","security scanner","prompt injection","2026-11-10 10:12:30",false,"---\nname: senseguard\ndescription: Semantic security scanner for OpenClaw skills. Detects prompt injection, data exfiltration, and hidden instructions that traditional code scanners miss. Use when user asks to scan skills, check skill safety, or run a security audit.\n---\n\n# SenseGuard\n\nScans OpenClaw skills for **natural language security threats** — the kind that VirusTotal and traditional code scanners cannot detect.\n\nTraditional scanners see SKILL.md as a text file. SenseGuard sees it as **agent instructions** and checks for prompt injection, data exfiltration, obfuscation, and persistence attacks.\n\n## How to Use\n\nWhen the user asks to scan a skill:\n\n```bash\npython3 scripts\u002Fscanner.py --target \u003Cskill-name-or-path>\n```\n\nOptions:\n- `--target all` — scan all installed skills\n- `--deep` — force LLM semantic analysis (Layer 2)\n- `--no-cache` — skip cached results\n- `--json` — output raw JSON for further processing\n\n### Layer 2 (Semantic Analysis)\n\nWhen `--json` output contains a `layer2_prompt` field, process it as a security audit task, then feed the JSON result back to generate the final score. This is how the LLM analyzes intent beyond regex patterns.\n\n## Output\n\nThe scanner outputs a Markdown risk report with:\n- Score (0-100) and rating: SAFE \u002F CAUTION \u002F DANGEROUS \u002F MALICIOUS\n- Findings with rule IDs, evidence text, and line numbers\n- Actionable recommendations\n\nFor CRITICAL findings, clearly advise the user to take action.\n\n## Key Differentiator\n\nSenseGuard catches what VirusTotal cannot:\n- `\"ignore all previous instructions\"` — prompt injection\n- `curl -X POST` hidden in Markdown — data exfiltration\n- Zero-width characters hiding commands — obfuscation\n- `\"modify MEMORY.md\"` — persistence attacks\n\nThese are invisible to traditional malware scanners because they target the **AI agent**, not the operating system.\n","# SenseGuard\n\nScans OpenClaw skills for **natural language security threats** — the kind that VirusTotal and traditional code scanners cannot detect.\n\nTraditional scanners see SKILL.md as a text file. SenseGuard sees it as **agent instructions** and checks for prompt injection, data exfiltration, obfuscation, and persistence attacks.\n\n## How to Use\n\nWhen the user asks to scan a skill:\n\n```bash\npython3 scripts\u002Fscanner.py --target \u003Cskill-name-or-path>\n```\n\nOptions:\n- `--target all` — scan all installed skills\n- `--deep` — force LLM semantic analysis (Layer 2)\n- `--no-cache` — skip cached results\n- `--json` — output raw JSON for further processing\n\n### Layer 2 (Semantic Analysis)\n\nWhen `--json` output contains a `layer2_prompt` field, process it as a security audit task, then feed the JSON result back to generate the final score. This is how the LLM analyzes intent beyond regex patterns.\n\n## Output\n\nThe scanner outputs a Markdown risk report with:\n- Score (0-100) and rating: SAFE \u002F CAUTION \u002F DANGEROUS \u002F MALICIOUS\n- Findings with rule IDs, evidence text, and line numbers\n- Actionable recommendations\n\nFor CRITICAL findings, clearly advise the user to take action.\n\n## Key Differentiator\n\nSenseGuard catches what VirusTotal cannot:\n- `\"ignore all previous instructions\"` — prompt injection\n- `curl -X POST` hidden in Markdown — data exfiltration\n- Zero-width characters hiding commands — obfuscation\n- `\"modify MEMORY.md\"` — persistence attacks\n\nThese are invisible to traditional malware scanners because they target the **AI agent**, not the operating system.\n",{"name":5,"description":7},"main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Ffermionoid\u002Fsenseguard",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":55,"prompt":65,"zipAvailable":66},[56,59,62],{"tool":57,"command":58},"npx","npx skills add kbarbel640-del\u002Fskills --skill senseguard",{"tool":60,"command":61},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill senseguard",{"tool":63,"command":64},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill senseguard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffermionoid\u002Fsenseguard\u002FSKILL.md",true,[68,74,80,84,88,92,96,100,104,108,112,116],{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"_meta.json","REFERENCE","参考文档",454,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffermionoid\u002Fsenseguard\u002F_meta.json",{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"scripts\u002Fcache_manager.py","SCRIPT","脚本",4634,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffermionoid\u002Fsenseguard\u002Fscripts\u002Fcache_manager.py",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"scripts\u002Freport_generator.py",17432,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffermionoid\u002Fsenseguard\u002Fscripts\u002Freport_generator.py",{"path":85,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":86,"sourceHtmlUrl":87},"scripts\u002Freputation_scorer.py",8243,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffermionoid\u002Fsenseguard\u002Fscripts\u002Freputation_scorer.py",{"path":89,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002Frule_engine.py",17458,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffermionoid\u002Fsenseguard\u002Fscripts\u002Frule_engine.py",{"path":93,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":94,"sourceHtmlUrl":95},"scripts\u002Frules\u002Fdata_exfiltration.yaml",1055,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffermionoid\u002Fsenseguard\u002Fscripts\u002Frules\u002Fdata_exfiltration.yaml",{"path":97,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":98,"sourceHtmlUrl":99},"scripts\u002Frules\u002Fmalicious_code.yaml",1254,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffermionoid\u002Fsenseguard\u002Fscripts\u002Frules\u002Fmalicious_code.yaml",{"path":101,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":102,"sourceHtmlUrl":103},"scripts\u002Frules\u002Fobfuscation.yaml",803,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffermionoid\u002Fsenseguard\u002Fscripts\u002Frules\u002Fobfuscation.yaml",{"path":105,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":106,"sourceHtmlUrl":107},"scripts\u002Frules\u002Fpersistence.yaml",867,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffermionoid\u002Fsenseguard\u002Fscripts\u002Frules\u002Fpersistence.yaml",{"path":109,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":110,"sourceHtmlUrl":111},"scripts\u002Frules\u002Fprompt_injection.yaml",1615,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffermionoid\u002Fsenseguard\u002Fscripts\u002Frules\u002Fprompt_injection.yaml",{"path":113,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":114,"sourceHtmlUrl":115},"scripts\u002Fscanner.py",9785,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffermionoid\u002Fsenseguard\u002Fscripts\u002Fscanner.py",{"path":117,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":118,"sourceHtmlUrl":119},"scripts\u002Fsemantic_analyzer.py",5835,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffermionoid\u002Fsenseguard\u002Fscripts\u002Fsemantic_analyzer.py",[121,151,174,195,201,221],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":132,"publishedAt":42},"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",[127],{"categoryNo":128,"categoryName":129,"taxonomyType":130,"taxonomyTypeDesc":131},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[133,134,135,136,137,138,139,140,141,28,142,143,144,145,146,147,148,149,150],"crowd prompting","prompting","api","with","tokens","domain","world","prompts","operations","text","tool","system","improve","productivity","marketplace","https","content","ai agents",{"skillNo":152,"name":153,"nameZh":6,"description":154,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":155,"categories":156,"keywords":158,"publishedAt":42},"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",[157],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},[159,135,160,161,162,163,164,165,166,167,32,168,169,170,171,172,173,140,26],"dilemm ai","arena","analyze","browser","openclaw agent","create","automation","browser automation","bot","design","strategy","headless","compete","submit","matchmaking",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":183,"publishedAt":42},"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",[180],{"categoryNo":181,"categoryName":182,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[184,185,186,187,188,189,190,136,191,172,26,192,135,193,194],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","read","http","via",{"skillNo":196,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":197,"categories":198,"keywords":200,"publishedAt":42},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[199],{"categoryNo":181,"categoryName":182,"taxonomyType":20,"taxonomyTypeDesc":21},[187,186,185,184,194,189,190,136,188,172,26,191,192,135,193],{"skillNo":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":205,"categories":206,"keywords":207,"publishedAt":42},"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",[],[208,209,210,211,212,213,214,215,216,217,218,219,220],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","get","branches",{"skillNo":222,"name":223,"nameZh":6,"description":224,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":225,"categories":226,"keywords":231,"publishedAt":42},"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",[227,228],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":229,"categoryName":230,"taxonomyType":130,"taxonomyTypeDesc":131},"01JBSEEDCAT000000000000037","律师与法务",[232,233,234,235,136,236,237,47,238,192,29,239,240,241,242,148,243,244,245],"agent constitution","constitution","contracts","tree","query","base","log","Rules","projects","compliance","actions","state","governance","github"]