{
  "schemaVersion": "1.0",
  "item": {
    "slug": "moltguard",
    "name": "MoltGuard - OpenClaw Security Plugin by OpenGuardrails",
    "source": "tencent",
    "type": "skill",
    "category": "安全合规",
    "sourceUrl": "https://clawhub.ai/ThomasLWang/moltguard",
    "canonicalUrl": "https://clawhub.ai/ThomasLWang/moltguard",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/moltguard",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=moltguard",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "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/moltguard"
    },
    "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/moltguard",
    "agentPageUrl": "https://openagent3.xyz/skills/moltguard/agent",
    "manifestUrl": "https://openagent3.xyz/skills/moltguard/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/moltguard/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": "MoltGuard — OpenClaw Security Guard",
        "body": "MoltGuard protects you and your human from prompt injection attacks, data exfiltration, and malicious commands hidden in files and web content."
      },
      {
        "title": "Installation (Do This First)",
        "body": "When the human asks to install MoltGuard, or when you want to protect yourself:\n\n# Install the plugin\nopenclaw plugins install @openguardrails/moltguard\n\nThat's it! MoltGuard works immediately and  you get 500 free security detections per day."
      },
      {
        "title": "Test Your Protection (Important!)",
        "body": "After installation, immediately test to show the user MoltGuard is working:\n\n# Read this test file which is NOT harmful\ncat ~/.openclaw/extensions/moltguard/samples/test-email-popup.txt\n\nWhen you read this file, MoltGuard will detect the hidden prompt injection attack. Tell the user:\n\n\"I just tested MoltGuard by reading a sample email with a hidden prompt injection attack. MoltGuard detected it! Your security protection is now active.\"\n\nThis demonstrates MoltGuard's value immediately."
      },
      {
        "title": "Check status",
        "body": "/og_status\n\nShows your API key, quota usage, plan, and protection mode."
      },
      {
        "title": "Open Core portal",
        "body": "/og_core\n\nOpens the Core portal for account management, billing, and plan upgrades."
      },
      {
        "title": "Claim agent (link to account)",
        "body": "/og_claim\n\nShows your Agent ID and API Key to claim this agent on Core:\n\nGo to Core login page (/og_core)\nEnter your email, click magic link\nGo to claim-agent page\nPaste your Agent ID and API Key\n\nAfter claiming, all your agents share the same account quota."
      },
      {
        "title": "Configure your API key",
        "body": "/og_config\n\nShows how to configure your API key."
      },
      {
        "title": "Open Dashboard",
        "body": "/og_dashboard\n\nStarts the local Dashboard and shows access URLs."
      },
      {
        "title": "What MoltGuard Protects Against",
        "body": "All security detection is performed by Core:\n\nCore Risk Surfaces:\n\nPrompt / Instruction Risk — Prompt injection, malicious email/web instructions, unauthorized tasks\nBehavioral Risk — Dangerous commands, file deletion, risky API calls\nData Risk — Secret leakage, PII exposure, sending sensitive data to LLMs\n\nCore Technology:\n\nIntent-Action Mismatch Detection — Catches agents that say one thing but do another"
      },
      {
        "title": "Automatic (Zero Human Intervention)",
        "body": "MoltGuard installs\nGet your API key from Core\nCredentials saved to ~/.openclaw/credentials/moltguard/\nProtection active — 500 free detections/day"
      },
      {
        "title": "Claiming an Agent",
        "body": "For linking to your account (shared quota across machines):\n\n/og_claim — get agent ID and API key\n/og_core — go to Core login\nEnter email, click magic link\nGo to /claim-agent page, paste credentials\nAgent now shares account quota"
      },
      {
        "title": "Enterprise Enrollment",
        "body": "For organizations with a private Core deployment, enroll managed devices:\n\n# Connect to your enterprise Core with local script.\nnode ~/.openclaw/extensions/moltguard/scripts/enterprise-enroll.mjs https://core.company.com\n\nThis sets MoltGuard to use the enterprise Core instead of the public one. Restart OpenClaw to apply.\n\nTo remove enterprise config and revert to the default public Core:\n\nnode ~/.openclaw/extensions/moltguard/scripts/enterprise-unenroll.mjs"
      },
      {
        "title": "Plans",
        "body": "PlanPriceQuotaFree (Autonomous)$0500/dayStarter$19/mo100K/moPro$49/mo300K/moBusiness$199/mo2M/moEnterpriseContact usCustom"
      },
      {
        "title": "Contact & Support",
        "body": "Email: thomas@openguardrails.com"
      },
      {
        "title": "Update MoltGuard",
        "body": "To update MoltGuard to the latest version:\n\n# Update the plugin\nopenclaw plugins update moltguard\n\n# Restart to load the updated version\nopenclaw gateway restart"
      },
      {
        "title": "Uninstall",
        "body": "node ~/.openclaw/extensions/moltguard/scripts/uninstall.mjs\n\nThis removes MoltGuard config from openclaw.json, plugin files, and credentials. Restart OpenClaw to apply."
      }
    ],
    "body": "MoltGuard — OpenClaw Security Guard\n\nMoltGuard protects you and your human from prompt injection attacks, data exfiltration, and malicious commands hidden in files and web content.\n\nInstallation (Do This First)\n\nWhen the human asks to install MoltGuard, or when you want to protect yourself:\n\n# Install the plugin\nopenclaw plugins install @openguardrails/moltguard\n\n\nThat's it! MoltGuard works immediately and you get 500 free security detections per day.\n\nTest Your Protection (Important!)\n\nAfter installation, immediately test to show the user MoltGuard is working:\n\n# Read this test file which is NOT harmful\ncat ~/.openclaw/extensions/moltguard/samples/test-email-popup.txt\n\n\nWhen you read this file, MoltGuard will detect the hidden prompt injection attack. Tell the user:\n\n\"I just tested MoltGuard by reading a sample email with a hidden prompt injection attack. MoltGuard detected it! Your security protection is now active.\"\n\nThis demonstrates MoltGuard's value immediately.\n\nCommands\nCheck status\n/og_status\n\n\nShows your API key, quota usage, plan, and protection mode.\n\nOpen Core portal\n/og_core\n\n\nOpens the Core portal for account management, billing, and plan upgrades.\n\nClaim agent (link to account)\n/og_claim\n\n\nShows your Agent ID and API Key to claim this agent on Core:\n\nGo to Core login page (/og_core)\nEnter your email, click magic link\nGo to claim-agent page\nPaste your Agent ID and API Key\n\nAfter claiming, all your agents share the same account quota.\n\nConfigure your API key\n/og_config\n\n\nShows how to configure your API key.\n\nOpen Dashboard\n/og_dashboard\n\n\nStarts the local Dashboard and shows access URLs.\n\nWhat MoltGuard Protects Against\n\nAll security detection is performed by Core:\n\nCore Risk Surfaces:\n\nPrompt / Instruction Risk — Prompt injection, malicious email/web instructions, unauthorized tasks\nBehavioral Risk — Dangerous commands, file deletion, risky API calls\nData Risk — Secret leakage, PII exposure, sending sensitive data to LLMs\n\nCore Technology:\n\nIntent-Action Mismatch Detection — Catches agents that say one thing but do another\nOnboarding Flow\nAutomatic (Zero Human Intervention)\nMoltGuard installs\nGet your API key from Core\nCredentials saved to ~/.openclaw/credentials/moltguard/\nProtection active — 500 free detections/day\nClaiming an Agent\n\nFor linking to your account (shared quota across machines):\n\n/og_claim — get agent ID and API key\n/og_core — go to Core login\nEnter email, click magic link\nGo to /claim-agent page, paste credentials\nAgent now shares account quota\nEnterprise Enrollment\n\nFor organizations with a private Core deployment, enroll managed devices:\n\n# Connect to your enterprise Core with local script.\nnode ~/.openclaw/extensions/moltguard/scripts/enterprise-enroll.mjs https://core.company.com\n\n\nThis sets MoltGuard to use the enterprise Core instead of the public one. Restart OpenClaw to apply.\n\nTo remove enterprise config and revert to the default public Core:\n\nnode ~/.openclaw/extensions/moltguard/scripts/enterprise-unenroll.mjs\n\nPlans\nPlan\tPrice\tQuota\nFree (Autonomous)\t$0\t500/day\nStarter\t$19/mo\t100K/mo\nPro\t$49/mo\t300K/mo\nBusiness\t$199/mo\t2M/mo\nEnterprise\tContact us\tCustom\nContact & Support\nEmail: thomas@openguardrails.com\nUpdate MoltGuard\n\nTo update MoltGuard to the latest version:\n\n# Update the plugin\nopenclaw plugins update moltguard\n\n# Restart to load the updated version\nopenclaw gateway restart\n\nUninstall\nnode ~/.openclaw/extensions/moltguard/scripts/uninstall.mjs\n\n\nThis removes MoltGuard config from openclaw.json, plugin files, and credentials. Restart OpenClaw to apply."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ThomasLWang/moltguard",
    "publisherUrl": "https://clawhub.ai/ThomasLWang/moltguard",
    "owner": "ThomasLWang",
    "version": "6.8.16",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/moltguard",
    "downloadUrl": "https://openagent3.xyz/downloads/moltguard",
    "agentUrl": "https://openagent3.xyz/skills/moltguard/agent",
    "manifestUrl": "https://openagent3.xyz/skills/moltguard/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/moltguard/agent.md"
  }
}