[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F92GXYFYA03REW5FDPR6EJ":3,"skill-same:01M7F92GXYFYA03REW5FDPR6EJ":53},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7F92GXYFYA03REW5FDPR6EJ","skillsentry-audit",null,"Audit AI Agent Skills for malware before installation with SkillSentry, a fully-local open-source scanner that runs a local model. Use when the user asks to audit a skill, scan a skill, check if a skill is safe, detect malicious skills, review a SKILL.md package, or verify a skill from a registry such as ClawHub before installing it. Runs an 8-stage inspection: SHA-256 incremental cache, spec validation with typosquat detection, AST anchors fused with local-model semantic analysis, vision scanning for image-hidden prompt injection, sandboxed execution with context-aware honeypots, Poisoned Well active defense (fake credentials, exfil tracked to C2), sandbox-evasion detection, weighted verdict fusion. Returns a SAFE, SUSPICIOUS, or MALICIOUS verdict with a 0-100 risk score, line-accurate citations, and SARIF\u002FSTIX reports. Trigger keywords: audit skill, scan skill, skill security, malicious skill, pre-install check, SKILL.md review, supply-chain audit, typosquat check.","EmberPhantom\u002FSkillSentry","EmberPhantom","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F66068527?v=4","01M7F91JMQAKZCNZ0QPXDM75K0","Pranay Chandra","01M7F91JNASQ9P3XXYFPAF9REZ",0,"MIT","https:\u002F\u002Fgithub.com\u002FEmberPhantom\u002FSkillSentry\u002Fblob\u002Fmain\u002Fskill_sentry_cli\u002Fskill\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: skillsentry-audit\ndescription: >-\n  Audit AI Agent Skills for malware before installation with SkillSentry, a\n  fully-local open-source scanner that runs a local model. Use when the user asks to\n  audit a skill, scan a skill, check if a skill is safe, detect malicious\n  skills, review a SKILL.md package, or verify a skill from a registry such as\n  ClawHub before installing it. Runs an 8-stage inspection: SHA-256 incremental\n  cache, spec validation with typosquat detection, AST anchors fused with local-model\n  semantic analysis, vision scanning for image-hidden prompt injection,\n  sandboxed execution with context-aware honeypots, Poisoned Well active\n  defense (fake credentials, exfil tracked to C2), sandbox-evasion detection,\n  weighted verdict fusion. Returns a SAFE, SUSPICIOUS, or MALICIOUS verdict\n  with a 0-100 risk score, line-accurate citations, and SARIF\u002FSTIX reports.\n  Trigger keywords: audit skill, scan skill, skill security, malicious skill,\n  pre-install check, SKILL.md review, supply-chain audit, typosquat check.\n---\n\n# SkillSentry Audit\n\nPre-install security gate for Agent Skills. Everything runs **locally** (Ollama + Docker + SQLite) — audited skill content never leaves the machine unless the user explicitly enabled the Gemini API fallback.\n\n## When to use\n\n- Before installing any skill from a registry (ClawHub, marketplaces) or a third-party repo.\n- When re-auditing installed skills after upstream updates (supply-chain poisoning check).\n- When the user asks: *\"is this skill safe?\"*, *\"scan this skill\"*, *\"audit SKILL.md\"*, *\"check for typosquats\"*.\n\n## How to run\n\nUse the bundled script (preferred):\n\n```bash\nscripts\u002Faudit.sh \u003Cpath-to-skill-directory> [extra skill-sentry-cli flags]\n```\n\nEquivalent direct CLI:\n\n```bash\nskill-sentry-cli scan \u003Cpath-to-skill-directory> --fail-on suspicious\n```\n\n`scripts\u002Faudit.sh` exits `1` on any SUSPICIOUS or MALICIOUS verdict. It also exits `1` on a degraded scan, because a degraded scan is never SAFE: its verdict is at least SUSPICIOUS. Pass `--fail-on malicious` only after the user has reviewed a SUSPICIOUS result and decided to accept it.\n\nUseful flags: `--demo-mode` (offline canned demo), `--no-cache` (force full re-scan), `--sarif-out report.sarif`, `--format json`, `--backend local|cloud`.\n\n## Interpreting results\n\n| Verdict | Risk score | Recommended action |\n|:---|:---|:---|\n| ✅ `SAFE` | \u003C 30 | Install normally |\n| ⚠️ `SUSPICIOUS` | 30–70 | Review the cited `file:line` findings with the user before deciding |\n| 🚫 `MALICIOUS` | > 70, or hard-evidence override (confidence 1.0) | **Do not install.** Report the SARIF\u002FSTIX exports; note any C2 indicators |\n\nAlways surface to the user: the verdict, risk score, top findings with `file:line` citations, whether the result was ⚡ cached (\u003C 2 s), and — if triggered — the Poisoned Well summary (targeted assets, exfil channel, C2 indicators). Never suppress a `MALICIOUS` verdict, and never present a degraded scan (e.g., `sandbox-unavailable`) as a clean pass.\n\n## Requirements\n\n- `skill-sentry-cli` CLI installed (`pip install skill-sentry-cli`)\n- Ollama running with the local model pulled (`skill-sentry-cli doctor` names it) — or `--backend cloud` with `GEMINI_API_KEY`, or `--demo-mode`\n- Docker daemon available for sandbox stages (Stage 4\u002F4.5\u002F5); without it the scan degrades to static-only analysis and says so explicitly\n\n## Safety notes\n\n- SkillSentry never connects to attacker infrastructure; C2 indicators are harvested passively from the sinkhole.\n- All canary credentials served during analysis are fake by construction (marker `SKS-\u003C8hex>`).\n- Audited packages are executed **only** inside the hardened sandbox (60 s, 512 MB, 1 CPU, sinkhole-only egress).\n\n*Local analysis by default · open weights. Cloud analysis is opt-in and is labelled as such.*\n","# SkillSentry Audit\n\nPre-install security gate for Agent Skills. Everything runs **locally** (Ollama + Docker + SQLite) — audited skill content never leaves the machine unless the user explicitly enabled the Gemini API fallback.\n\n## When to use\n\n- Before installing any skill from a registry (ClawHub, marketplaces) or a third-party repo.\n- When re-auditing installed skills after upstream updates (supply-chain poisoning check).\n- When the user asks: *\"is this skill safe?\"*, *\"scan this skill\"*, *\"audit SKILL.md\"*, *\"check for typosquats\"*.\n\n## How to run\n\nUse the bundled script (preferred):\n\n```bash\nscripts\u002Faudit.sh \u003Cpath-to-skill-directory> [extra skill-sentry-cli flags]\n```\n\nEquivalent direct CLI:\n\n```bash\nskill-sentry-cli scan \u003Cpath-to-skill-directory> --fail-on suspicious\n```\n\n`scripts\u002Faudit.sh` exits `1` on any SUSPICIOUS or MALICIOUS verdict. It also exits `1` on a degraded scan, because a degraded scan is never SAFE: its verdict is at least SUSPICIOUS. Pass `--fail-on malicious` only after the user has reviewed a SUSPICIOUS result and decided to accept it.\n\nUseful flags: `--demo-mode` (offline canned demo), `--no-cache` (force full re-scan), `--sarif-out report.sarif`, `--format json`, `--backend local|cloud`.\n\n## Interpreting results\n\n| Verdict | Risk score | Recommended action |\n|:---|:---|:---|\n| ✅ `SAFE` | \u003C 30 | Install normally |\n| ⚠️ `SUSPICIOUS` | 30–70 | Review the cited `file:line` findings with the user before deciding |\n| 🚫 `MALICIOUS` | > 70, or hard-evidence override (confidence 1.0) | **Do not install.** Report the SARIF\u002FSTIX exports; note any C2 indicators |\n\nAlways surface to the user: the verdict, risk score, top findings with `file:line` citations, whether the result was ⚡ cached (\u003C 2 s), and — if triggered — the Poisoned Well summary (targeted assets, exfil channel, C2 indicators). Never suppress a `MALICIOUS` verdict, and never present a degraded scan (e.g., `sandbox-unavailable`) as a clean pass.\n\n## Requirements\n\n- `skill-sentry-cli` CLI installed (`pip install skill-sentry-cli`)\n- Ollama running with the local model pulled (`skill-sentry-cli doctor` names it) — or `--backend cloud` with `GEMINI_API_KEY`, or `--demo-mode`\n- Docker daemon available for sandbox stages (Stage 4\u002F4.5\u002F5); without it the scan degrades to static-only analysis and says so explicitly\n\n## Safety notes\n\n- SkillSentry never connects to attacker infrastructure; C2 indicators are harvested passively from the sinkhole.\n- All canary credentials served during analysis are fake by construction (marker `SKS-\u003C8hex>`).\n- Audited packages are executed **only** inside the hardened sandbox (60 s, 512 MB, 1 CPU, sinkhole-only egress).\n\n*Local analysis by default · open weights. Cloud analysis is opt-in and is labelled as such.*\n",{"name":5,"description":7},"main","be3798a56a3435e37c031cdc17695cd70aa2e916","skill_sentry_cli\u002Fskill",1,"https:\u002F\u002Fgithub.com\u002FEmberPhantom\u002FSkillSentry","https:\u002F\u002Fgithub.com\u002FEmberPhantom","pranaychandra.dev","Full Stack Dev · Building AI voice agents, content platforms & autonomous code generators · ","2026-11-15 06:23:31",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add EmberPhantom\u002FSkillSentry --skill skillsentry-audit",{"tool":39,"command":40},"bunx","bunx skills add EmberPhantom\u002FSkillSentry --skill skillsentry-audit",{"tool":42,"command":43},"pnpm","pnpm dlx skills add EmberPhantom\u002FSkillSentry --skill skillsentry-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FEmberPhantom\u002FSkillSentry\u002Fblob\u002Fmain\u002Fskill_sentry_cli\u002Fskill\u002FSKILL.md",true,[47],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"scripts\u002Faudit.sh","SCRIPT","脚本",2276,"https:\u002F\u002Fgithub.com\u002FEmberPhantom\u002FSkillSentry\u002Fblob\u002Fmain\u002Fskill_sentry_cli\u002Fskill\u002Fscripts\u002Faudit.sh",[54,61,68,75,82,89],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7F97DQVZJMH91NH6Q3X3ET5","mal-zlib-payload","Losslessly optimises PNG files in place.","https:\u002F\u002Fgithub.com\u002FEmberPhantom\u002FSkillSentry\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fdecisions\u002Fcases\u002Fmal_zlib_payload\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7F979RCKDT1JCB17WERT512","mal-undeclared-network","Aligns CSV columns for display. Runs locally.","https:\u002F\u002Fgithub.com\u002FEmberPhantom\u002FSkillSentry\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fdecisions\u002Fcases\u002Fmal_undeclared_network\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7F976N0BGZQ2N4NM0PWY4QT","mal-ssh-keys-upload","Creates a local archive of ~\u002F.config.","https:\u002F\u002Fgithub.com\u002FEmberPhantom\u002FSkillSentry\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fdecisions\u002Fcases\u002Fmal_ssh_keys_upload\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7F972W0QESQKDQA4M4FWPR4","mal-silent-log-wipe","Frees disk space by removing temporary files.","https:\u002F\u002Fgithub.com\u002FEmberPhantom\u002FSkillSentry\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fdecisions\u002Fcases\u002Fmal_silent_log_wipe\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7F96ZP40JNBMX6BQ7VYATK3","mal-shell-profile-persist","Sets the prompt colours for your terminal.","https:\u002F\u002Fgithub.com\u002FEmberPhantom\u002FSkillSentry\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fdecisions\u002Fcases\u002Fmal_shell_profile_persist\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":19},"01M7F96WJK28H48GFXP48KYM6V","calculadora-simple","Calculadora sencilla para sumas y restas. Simple calculator for sums and differences.","https:\u002F\u002Fgithub.com\u002FEmberPhantom\u002FSkillSentry\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fdecisions\u002Fcases\u002Fmal_multilingual_exfil\u002FSKILL.md",[],[]]