[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7D481KTYN5S7X3ET4ESF634":3,"skill-same:01M7D481KTYN5S7X3ET4ESF634":47},{"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},"01M7D481KTYN5S7X3ET4ESF634","repo-ioc-sweep",null,"Inventory what a codebase talks to - extract embedded URLs, IPs, domains, wallets, base64 blobs and shell scripts from a repo, then enrich each endpoint through mlab.sh. Use when the user asks what a repo connects to, wants an egress inventory, or vets a vendor\u002Fthird-party codebase for suspicious embedded infrastructure.","mlab-sh\u002Fmlab-claude","mlab-sh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F197380970?v=4","01M7D45Z8NKEZYYHGF1F1HFZ00","Mlab.sh","01M7D45Z9FXN34R73J4E5D9F63",1,"MIT","https:\u002F\u002Fgithub.com\u002Fmlab-sh\u002Fmlab-claude\u002Fblob\u002Fmain\u002Fplugins\u002Fmlab\u002Fskills\u002Frepo-ioc-sweep\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: repo-ioc-sweep\ndescription: Inventory what a codebase talks to - extract embedded URLs, IPs, domains, wallets, base64 blobs and shell scripts from a repo, then enrich each endpoint through mlab.sh. Use when the user asks what a repo connects to, wants an egress inventory, or vets a vendor\u002Fthird-party codebase for suspicious embedded infrastructure.\n---\n\n# Repo IOC Sweep\n\n> mlab output shapes: `${CLAUDE_PLUGIN_ROOT}\u002Fdocs\u002Ftool-reference.md`.\n\n\"This repo talks to whom?\" Answer with an inventory, then a verdict per endpoint. Dependency CODE is supply-chain-audit's job; this skill sweeps the repo's own files.\n\n## Workflow\n\n### 1. Extract\n\nSweep tracked text files (skip vendored deps, lockfiles, node_modules, minified bundles, test fixtures unless asked) with grep\u002Fripgrep for:\n- URLs and bare domains (config files, source, CI workflows, Dockerfiles, install docs)\n- IP literals (both in code and in configs - an IP literal in source is a finding by itself)\n- crypto wallet shapes (BTC\u002FEVM\u002FSOL patterns)\n- long base64\u002Fhex blobs (decode ONE layer locally, never execute; re-sweep the decoded content)\n- webhooks, telemetry endpoints, update URLs, package registries beyond the defaults\n\nShell scripts in the repo (install.sh, CI steps, hooks) → `scan_bash` each: it flags dangerous constructs and extracts IOCs for you.\n\n### 2. Classify before enriching\n\nDedupe, then bucket: documentation-only (README badges, examples) \u002F build-time (CI, registries) \u002F runtime (code paths that will fire in production). Runtime endpoints matter most; say which bucket each finding sits in.\n\n### 3. Enrich\n\n`detect_ioc` on ambiguous strings; `scan_url` per URL; `scan_ip` on IP literals (quota - `get_scan_limits` first on large sets, budget like ioc-batch); `scan_crypto` on wallets (crypto quota, chain rules); domain scans only for the few domains central to the verdict.\n\n### 4. Report\n\n```\n## Egress inventory: \u003Crepo>\n\n**Verdict:** \u003Cexpected profile | surprises found | suspicious>\n\n| Endpoint | Where (file:line) | Bucket | Verdict | Evidence |\n\n### Surprises\n\u003Canything a user of this software would not expect it to contact - with the code path>\n\n### Wallets \u002F blobs\n\u003Cdecoded layers, what they contained>\n\n### Blocklist candidates\n\u003Cdefanged>\n```\n\n## Rules\n\n- Every finding carries file:line; an inventory without locations cannot be acted on.\n- An endpoint being unknown to mlab is not a finding; an endpoint UNEXPECTED for this software is - argue from purpose.\n- Decode blobs statically only; never run repo code to observe its traffic.\n","# Repo IOC Sweep\n\n> mlab output shapes: `${CLAUDE_PLUGIN_ROOT}\u002Fdocs\u002Ftool-reference.md`.\n\n\"This repo talks to whom?\" Answer with an inventory, then a verdict per endpoint. Dependency CODE is supply-chain-audit's job; this skill sweeps the repo's own files.\n\n## Workflow\n\n### 1. Extract\n\nSweep tracked text files (skip vendored deps, lockfiles, node_modules, minified bundles, test fixtures unless asked) with grep\u002Fripgrep for:\n- URLs and bare domains (config files, source, CI workflows, Dockerfiles, install docs)\n- IP literals (both in code and in configs - an IP literal in source is a finding by itself)\n- crypto wallet shapes (BTC\u002FEVM\u002FSOL patterns)\n- long base64\u002Fhex blobs (decode ONE layer locally, never execute; re-sweep the decoded content)\n- webhooks, telemetry endpoints, update URLs, package registries beyond the defaults\n\nShell scripts in the repo (install.sh, CI steps, hooks) → `scan_bash` each: it flags dangerous constructs and extracts IOCs for you.\n\n### 2. Classify before enriching\n\nDedupe, then bucket: documentation-only (README badges, examples) \u002F build-time (CI, registries) \u002F runtime (code paths that will fire in production). Runtime endpoints matter most; say which bucket each finding sits in.\n\n### 3. Enrich\n\n`detect_ioc` on ambiguous strings; `scan_url` per URL; `scan_ip` on IP literals (quota - `get_scan_limits` first on large sets, budget like ioc-batch); `scan_crypto` on wallets (crypto quota, chain rules); domain scans only for the few domains central to the verdict.\n\n### 4. Report\n\n```\n## Egress inventory: \u003Crepo>\n\n**Verdict:** \u003Cexpected profile | surprises found | suspicious>\n\n| Endpoint | Where (file:line) | Bucket | Verdict | Evidence |\n\n### Surprises\n\u003Canything a user of this software would not expect it to contact - with the code path>\n\n### Wallets \u002F blobs\n\u003Cdecoded layers, what they contained>\n\n### Blocklist candidates\n\u003Cdefanged>\n```\n\n## Rules\n\n- Every finding carries file:line; an inventory without locations cannot be acted on.\n- An endpoint being unknown to mlab is not a finding; an endpoint UNEXPECTED for this software is - argue from purpose.\n- Decode blobs statically only; never run repo code to observe its traffic.\n",{"name":5,"description":7},"main","0678f3559c0b5576fd964874a3debae3f6b5a31c","plugins\u002Fmlab\u002Fskills\u002Frepo-ioc-sweep",0,"https:\u002F\u002Fgithub.com\u002Fmlab-sh\u002Fmlab-claude","https:\u002F\u002Fgithub.com\u002Fmlab-sh","https:\u002F\u002Fmlab.sh","MLAB is a modular security analysis platform for IOC analysis at scale","2026-10-22 03:39:43",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add mlab-sh\u002Fmlab-claude --skill repo-ioc-sweep",{"tool":39,"command":40},"bunx","bunx skills add mlab-sh\u002Fmlab-claude --skill repo-ioc-sweep",{"tool":42,"command":43},"pnpm","pnpm dlx skills add mlab-sh\u002Fmlab-claude --skill repo-ioc-sweep","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmlab-sh\u002Fmlab-claude\u002Fblob\u002Fmain\u002Fplugins\u002Fmlab\u002Fskills\u002Frepo-ioc-sweep\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7D494QGV4DTD8PE8NTDHRM4","threat-watch","Generate a threat landscape digest from mlab.sh - recent critical\u002FKEV CVEs filtered to a declared technology stack, with actor attribution. Use when the user asks what is new in vulnerabilities, wants a daily\u002Fweekly threat brief, asks about recent CVEs for a product, or sets up a recurring watch on their stack.","https:\u002F\u002Fgithub.com\u002Fmlab-sh\u002Fmlab-claude\u002Fblob\u002Fmain\u002Fplugins\u002Fmlab\u002Fskills\u002Fthreat-watch\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7D48Z3YTQN4ZHMGTH1EXXR5","supply-chain-audit","Full supply-chain audit of a project - postmortem detects malicious code, install hooks and risky dependencies locally, then mlab.sh enriches what it finds (hashes, endpoints, actors, CVEs). Use when the user asks to audit a project's dependencies or supply chain, check a repo for malicious packages, or vet a codebase before adoption or deployment.","https:\u002F\u002Fgithub.com\u002Fmlab-sh\u002Fmlab-claude\u002Fblob\u002Fmain\u002Fplugins\u002Fmlab\u002Fskills\u002Fsupply-chain-audit\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7D48RXRAHKVAE6SWQT2EN6H","smishing-campaign","Analyze a batch of reported SMS\u002Ftext messages through mlab.sh - score each for smishing, cluster them into campaigns, and extract the shared infrastructure (URLs, callback numbers, sender patterns). Use when the user has multiple reported SMS from users\u002Femployees, or investigates an SMS phishing wave. For a single message, phishing-triage does the job.","https:\u002F\u002Fgithub.com\u002Fmlab-sh\u002Fmlab-claude\u002Fblob\u002Fmain\u002Fplugins\u002Fmlab\u002Fskills\u002Fsmishing-campaign\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7D48KBNYFBJNS9MEHHWMW80","script-triage","Statically analyze a suspicious shell script through mlab.sh - install.sh, cron payloads, CI steps, curl-pipe-sh one-liners. Flags dangerous constructs (download-piped-to-shell, base64 decoding, reverse shells, persistence, anti-forensics, destructive deletes), extracts every IOC and enriches them. Use when the user pastes shell code and asks if it is safe\u002Fmalicious, or provides a .sh file to vet before running it.","https:\u002F\u002Fgithub.com\u002Fmlab-sh\u002Fmlab-claude\u002Fblob\u002Fmain\u002Fplugins\u002Fmlab\u002Fskills\u002Fscript-triage\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7D48E9ZYDPAN85NXAED50E6","sbom-export","Generate a CycloneDX SBOM locally with postmortem and push it through mlab.sh vulnerability scanning - for projects or container images where no single lockfile can be pasted. Use when the user asks for an SBOM, needs vuln scanning of a container image or a multi-ecosystem repo, or when sbom-audit lacks a usable lockfile.","https:\u002F\u002Fgithub.com\u002Fmlab-sh\u002Fmlab-claude\u002Fblob\u002Fmain\u002Fplugins\u002Fmlab\u002Fskills\u002Fsbom-export\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7D487A4AZ6KK5CV214QG013","sbom-audit","Audit a dependency lockfile or SBOM for known vulnerabilities via mlab.sh, prioritize findings by KEV status and EPSS, and attribute actively exploited CVEs to threat actors. Use when the user provides a lockfile (package-lock.json, yarn.lock, pnpm-lock.yaml, Cargo.lock, requirements.txt, poetry.lock, uv.lock, Pipfile.lock, go.sum, composer.lock, Gemfile.lock, pom.xml, gradle.lockfile, packages.lock.json, pubspec.lock, mix.lock) or a CycloneDX \u002F SPDX SBOM, or asks to check dependencies for vulnerabilities.","https:\u002F\u002Fgithub.com\u002Fmlab-sh\u002Fmlab-claude\u002Fblob\u002Fmain\u002Fplugins\u002Fmlab\u002Fskills\u002Fsbom-audit\u002FSKILL.md",[],[]]