[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JZ8VCBPZ67S4CTRMX2NHTZ":3,"skill-same:01M6JZ8VCBPZ67S4CTRMX2NHTZ":74},{"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":23,"publishedAt":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":55,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":58,"updatedAt":59,"install":60,"resources":73},"01M6JZ8VCBPZ67S4CTRMX2NHTZ","hol-guard",null,"Run HOL Guard scanner and guard operations via `uv run hol-guard`. Use when the user asks to scan plugins\u002FMCP\u002Fskills for security, quality, or ecosystem compliance, or when they ask to run guard detect\u002Finstall\u002Fprotect workflows for local AI harnesses.","hashgraph-online\u002Fhol-guard","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JZ7VJRA75Y6F8FFRWZMM11",1090,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fhol-guard\u002Fblob\u002Fmain\u002F.factory\u002Fskills\u002Fhol-guard\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"hol guard","guard","local ai","when","for","harnesses","ecosystem","detect","local","guard scanner","scan","scanner","MCP","uv run","uv","use","install","ask","run","workflows","security","2026-11-10 10:12:30",false,"---\nname: hol-guard\ndescription: Run HOL Guard scanner and guard operations via `uv run hol-guard`. Use when the user asks to scan plugins\u002FMCP\u002Fskills for security, quality, or ecosystem compliance, or when they ask to run guard detect\u002Finstall\u002Fprotect workflows for local AI harnesses.\n---\n\n# HOL Guard\n\nHOL Guard is an AI Antivirus scanner that checks plugins, MCP servers, skills, and local AI harnesses for security, quality, and ecosystem compliance.\n\n## Prerequisites\n\n- Always run from the `hol-guard` project root.\n- Use `uv run hol-guard` to invoke the CLI. Never invoke Python modules directly.\n- Ensure `uv sync --frozen --extra dev` has been run before invoking.\n\n## Scanner Operations\n\nScan a plugin or skill directory:\n\n```\nuv run hol-guard scan \u003Cdirectory> [--format json|text|markdown|sarif] [--profile default|public-marketplace|strict-security] [--fail-on-severity critical|high|medium|low|info|none]\n```\n\nLint rules:\n\n```\nuv run hol-guard lint \u003Cdirectory> [--list-rules] [--explain \u003Crule-id>]\n```\n\nVerify runtime:\n\n```\nuv run hol-guard verify \u003Cdirectory> [--online]\n```\n\nList ecosystems:\n\n```\nuv run hol-guard --list-ecosystems\n```\n\n## Guard Operations\n\nDetect harnesses:\n\n```\nuv run hol-guard detect [codex|claude|cursor|gemini|opencode] [--json]\n```\n\nRun guard in dry-run mode:\n\n```\nuv run hol-guard run \u003Charness> --dry-run --default-action allow --json\n```\n\nCheck guard status:\n\n```\nuv run hol-guard status [--json]\n```\n\n## Common Test Fixtures\n\nTest fixtures live in `tests\u002Ffixtures\u002F`:\n- `good-plugin\u002F` - clean Codex plugin with all required fields\n- `bad-plugin\u002F` - plugin with secrets, missing fields, bad practices\n- `malicious-skill-plugin\u002F` - skill with malicious patterns\n- `multi-ecosystem-repo\u002F` - repo with Codex, Claude, and Gemini configs\n- `claude-plugin-good\u002F` - clean Claude plugin\n- `opencode-good\u002F` - clean OpenCode plugin\n- `gemini-extension-good\u002F` - clean Gemini extension\n\n## Verification\n\nAfter each operation, verify:\n- Exit code 0 for clean targets\n- Exit code non-zero for targets with findings\n- Output is valid JSON when `--format json` or `--json` is used\n- Scanner reports findings with correct rule IDs and severities\n","# HOL Guard\n\nHOL Guard is an AI Antivirus scanner that checks plugins, MCP servers, skills, and local AI harnesses for security, quality, and ecosystem compliance.\n\n## Prerequisites\n\n- Always run from the `hol-guard` project root.\n- Use `uv run hol-guard` to invoke the CLI. Never invoke Python modules directly.\n- Ensure `uv sync --frozen --extra dev` has been run before invoking.\n\n## Scanner Operations\n\nScan a plugin or skill directory:\n\n```\nuv run hol-guard scan \u003Cdirectory> [--format json|text|markdown|sarif] [--profile default|public-marketplace|strict-security] [--fail-on-severity critical|high|medium|low|info|none]\n```\n\nLint rules:\n\n```\nuv run hol-guard lint \u003Cdirectory> [--list-rules] [--explain \u003Crule-id>]\n```\n\nVerify runtime:\n\n```\nuv run hol-guard verify \u003Cdirectory> [--online]\n```\n\nList ecosystems:\n\n```\nuv run hol-guard --list-ecosystems\n```\n\n## Guard Operations\n\nDetect harnesses:\n\n```\nuv run hol-guard detect [codex|claude|cursor|gemini|opencode] [--json]\n```\n\nRun guard in dry-run mode:\n\n```\nuv run hol-guard run \u003Charness> --dry-run --default-action allow --json\n```\n\nCheck guard status:\n\n```\nuv run hol-guard status [--json]\n```\n\n## Common Test Fixtures\n\nTest fixtures live in `tests\u002Ffixtures\u002F`:\n- `good-plugin\u002F` - clean Codex plugin with all required fields\n- `bad-plugin\u002F` - plugin with secrets, missing fields, bad practices\n- `malicious-skill-plugin\u002F` - skill with malicious patterns\n- `multi-ecosystem-repo\u002F` - repo with Codex, Claude, and Gemini configs\n- `claude-plugin-good\u002F` - clean Claude plugin\n- `opencode-good\u002F` - clean OpenCode plugin\n- `gemini-extension-good\u002F` - clean Gemini extension\n\n## Verification\n\nAfter each operation, verify:\n- Exit code 0 for clean targets\n- Exit code non-zero for targets with findings\n- Output is valid JSON when `--format json` or `--json` is used\n- Scanner reports findings with correct rule IDs and severities\n",{"name":5,"description":7},"main","84e6821e351717b1641f5dd3578f38bc09388cbf",".factory\u002Fskills\u002Fhol-guard",267,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fhol-guard","https:\u002F\u002Fhol.org\u002Fguard","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-12 04:28:51",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add hashgraph-online\u002Fhol-guard --skill hol-guard",{"tool":66,"command":67},"bunx","bunx skills add hashgraph-online\u002Fhol-guard --skill hol-guard",{"tool":69,"command":70},"pnpm","pnpm dlx skills add hashgraph-online\u002Fhol-guard --skill hol-guard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fhol-guard\u002Fblob\u002Fmain\u002F.factory\u002Fskills\u002Fhol-guard\u002FSKILL.md",true,[],[75,84,95,101,115,129],{"skillNo":76,"name":77,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":81,"publishedAt":45},"01M6JZAYM3E5SRWQXR4BZ14Z8R","bad-skill","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fhol-guard\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fskills-no-frontmatter\u002Fskills\u002Fbad-skill\u002FSKILL.md",[80],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[82,83],"bad","bad skill",{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":91,"publishedAt":45},"01M6JZAW3TXCB3F657DD225ZHP","example","Example repository plugin skill.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fhol-guard\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmulti-plugin-repo\u002Fplugins\u002Fbeta-plugin\u002Fskills\u002Fexample\u002FSKILL.md",[90],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[86,92,93,94],"plugin","repository","plugin skill",{"skillNo":96,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":100,"publishedAt":45},"01M6JZASJJ704QFHNJFKDSR2NR","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fhol-guard\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmulti-plugin-repo\u002Fplugins\u002Falpha-plugin\u002Fskills\u002Fexample\u002FSKILL.md",[99],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[86,92,93,94],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":108,"publishedAt":45},"01M6JZAPXVM5TD1TQP585PJPWX","using-demo","Recall project context.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fhol-guard\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fkimi-plugin-good\u002Fskills\u002Fusing-demo\u002FSKILL.md",[107],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[109,110,111,112,113,114],"demo","using demo","project context","recall","project","context",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":122,"publishedAt":45},"01M6JZAHZ4QVMRA1SAE62J7R5S","benign","A completely safe skill with no risk signals.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fhol-guard\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fhermes-plugin-evil\u002Fskills\u002Futils\u002Fbenign\u002FSKILL.md",[121],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[117,123,124,125,126,127,128],"with","helper","signals","safe skill","risk","safe",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":136,"publishedAt":45},"01M6JZAF2ZY9M2VK7BFHQ5TXG0","sneaky","Looks benign but has malicious subdirectory files.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fhol-guard\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fhermes-plugin-evil\u002Fskills\u002Fstealth\u002Fsneaky\u002FSKILL.md",[135],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[131,117,137,138,139,140,141],"fixture","stealth","but","files","malicious"]