{ "schemaVersion": "1.0", "item": { "slug": "clawguarddevin", "name": "Devin Floyd", "source": "tencent", "type": "skill", "category": "安全合规", "sourceUrl": "https://clawhub.ai/devinfloyd1/clawguarddevin", "canonicalUrl": "https://clawhub.ai/devinfloyd1/clawguarddevin", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/clawguarddevin", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=clawguarddevin", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "tests/fixtures/malicious_skill_exfil/SKILL.md", "tests/fixtures/malicious_skill_obfuscated/SKILL.md", "tests/fixtures/malicious_skill_revshell/SKILL.md", "tests/fixtures/malicious_skill_credential/SKILL.md", "tests/fixtures/clean_skill/SKILL.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/clawguarddevin" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/clawguarddevin", "agentPageUrl": "https://openagent3.xyz/skills/clawguarddevin/agent", "manifestUrl": "https://openagent3.xyz/skills/clawguarddevin/agent.json", "briefUrl": "https://openagent3.xyz/skills/clawguarddevin/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "ClawGuard", "body": "Security Scanner for OpenClaw/Clawdbot Skills\n\nProtect yourself from malicious skill installations. ClawGuard scans skills for dangerous patterns before you install them - including patterns from the ClawHavoc campaign (341 malicious skills discovered by Koi Security)." }, { "title": "Quick Start", "body": "# Scan a skill by name\npython scan.py --skill \n\n# Scan a skill by path \npython scan.py --path /path/to/skill\n\n# Scan all installed skills\npython scan.py --all" }, { "title": "What It Detects", "body": "CategoryExamplesSeverity🔴 Reverse Shellssocket.connect(), pty.spawn(), /dev/tcpCritical🔴 Data Exfiltrationrequests.post() to suspicious TLDsCritical🔴 Credential HarvestReading ~/.ssh/id_rsa, AWS credentialsCritical🔴 Obfuscationbase64.b64decode(exec), chr() chainsCritical🔴 ClawHavoc IOCsglot.io scripts, fake Apple URLs, known C2 IPsCritical🟠 Code Executionexec(), eval(), subprocessHigh🟡 Suspicious NetworkURL shorteners, weird portsMedium" }, { "title": "Output Formats", "body": "# Console (default) - colored terminal output\npython scan.py --skill github\n\n# JSON - machine-readable for CI/CD\npython scan.py --skill github --format json\n\n# Markdown - for sharing reports\npython scan.py --skill github --format markdown" }, { "title": "Risk Scoring", "body": "ScoreLevelAction0-10🟢 SafeInstall freely11-25🟢 LowQuick review26-50🟡 MediumReview findings51-75🔴 HighReview carefully76-100🔴 CriticalDo not install" }, { "title": "IOC Database", "body": "70+ indicators of compromise including:\n\nRemote access (reverse shells, C2)\nData exfiltration\nCredential harvesting\nCode obfuscation\nReal ClawHavoc campaign IOCs (from Koi Security research)\nKnown malicious IPs, hashes, and skill names" }, { "title": "Requirements", "body": "Python 3.8+\nNo external dependencies (stdlib only)" }, { "title": "Credits", "body": "IOCs enriched with research from Koi Security - ClawHavoc campaign analysis by Oren Yomtov and Alex." }, { "title": "Links", "body": "GitHub Repository\nClawHavoc Research\n\nBuilt for the Clawdbot community 🐾" } ], "body": "ClawGuard\n\nSecurity Scanner for OpenClaw/Clawdbot Skills\n\nProtect yourself from malicious skill installations. ClawGuard scans skills for dangerous patterns before you install them - including patterns from the ClawHavoc campaign (341 malicious skills discovered by Koi Security).\n\nQuick Start\n# Scan a skill by name\npython scan.py --skill \n\n# Scan a skill by path \npython scan.py --path /path/to/skill\n\n# Scan all installed skills\npython scan.py --all\n\nWhat It Detects\nCategory\tExamples\tSeverity\n🔴 Reverse Shells\tsocket.connect(), pty.spawn(), /dev/tcp\tCritical\n🔴 Data Exfiltration\trequests.post() to suspicious TLDs\tCritical\n🔴 Credential Harvest\tReading ~/.ssh/id_rsa, AWS credentials\tCritical\n🔴 Obfuscation\tbase64.b64decode(exec), chr() chains\tCritical\n🔴 ClawHavoc IOCs\tglot.io scripts, fake Apple URLs, known C2 IPs\tCritical\n🟠 Code Execution\texec(), eval(), subprocess\tHigh\n🟡 Suspicious Network\tURL shorteners, weird ports\tMedium\nOutput Formats\n# Console (default) - colored terminal output\npython scan.py --skill github\n\n# JSON - machine-readable for CI/CD\npython scan.py --skill github --format json\n\n# Markdown - for sharing reports\npython scan.py --skill github --format markdown\n\nRisk Scoring\nScore\tLevel\tAction\n0-10\t🟢 Safe\tInstall freely\n11-25\t🟢 Low\tQuick review\n26-50\t🟡 Medium\tReview findings\n51-75\t🔴 High\tReview carefully\n76-100\t🔴 Critical\tDo not install\nIOC Database\n\n70+ indicators of compromise including:\n\nRemote access (reverse shells, C2)\nData exfiltration\nCredential harvesting\nCode obfuscation\nReal ClawHavoc campaign IOCs (from Koi Security research)\nKnown malicious IPs, hashes, and skill names\nRequirements\nPython 3.8+\nNo external dependencies (stdlib only)\nCredits\n\nIOCs enriched with research from Koi Security - ClawHavoc campaign analysis by Oren Yomtov and Alex.\n\nLinks\nGitHub Repository\nClawHavoc Research\n\nBuilt for the Clawdbot community 🐾" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/devinfloyd1/clawguarddevin", "publisherUrl": "https://clawhub.ai/devinfloyd1/clawguarddevin", "owner": "devinfloyd1", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/clawguarddevin", "downloadUrl": "https://openagent3.xyz/downloads/clawguarddevin", "agentUrl": "https://openagent3.xyz/skills/clawguarddevin/agent", "manifestUrl": "https://openagent3.xyz/skills/clawguarddevin/agent.json", "briefUrl": "https://openagent3.xyz/skills/clawguarddevin/agent.md" } }