{
  "schemaVersion": "1.0",
  "item": {
    "slug": "promptdome",
    "name": "PromptDome",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/tschew72/promptdome",
    "canonicalUrl": "https://clawhub.ai/tschew72/promptdome",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/promptdome",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=promptdome",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "hook/HOOK.md",
      "hook/handler.ts",
      "plugin/index.ts",
      "plugin/openclaw.plugin.json",
      "scripts/setup.sh"
    ],
    "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": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.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/promptdome"
    },
    "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/promptdome",
    "agentPageUrl": "https://openagent3.xyz/skills/promptdome/agent",
    "manifestUrl": "https://openagent3.xyz/skills/promptdome/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/promptdome/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": "PromptDome × OpenClaw",
        "body": "API key required — Get yours free at https://promptdome.cyberforge.one/dashboard/api-keys\n(Sign up → Dashboard → API Keys → Create Key)\n\nAdds automatic prompt injection detection to any OpenClaw agent. Two components work together:\n\nComponentWhat it doesWhen it firespromptdome-gate hookAuto-scans every incoming message; injects ⚠️ warning if injection detectedEvery message:received — zero agent code requiredpromptdome_scan toolExplicit scan agent can call on any contentOn demand — web content, files, tool outputs"
      },
      {
        "title": "Quick Setup (60 seconds)",
        "body": "bash skills/promptdome/scripts/setup.sh --api-key sk_shield_live_YOUR_KEY\n\nThat's it. The script:\n\nTests your API key against the PromptDome API\nInstalls promptdome-gate hook → ~/.openclaw/hooks/promptdome-gate/\nInstalls promptdome_scan plugin → ~/.openclaw/extensions/promptdome/\nSaves API key to openclaw.json env block\nEnables the hook automatically\nPrompts you to restart the gateway\n\nGet an API key: https://promptdome.cyberforge.one/dashboard/api-keys"
      },
      {
        "title": "1. Copy files",
        "body": "# Hook (auto-scanning)\nmkdir -p ~/.openclaw/hooks/promptdome-gate\ncp skills/promptdome/hook/HOOK.md   ~/.openclaw/hooks/promptdome-gate/\ncp skills/promptdome/hook/handler.ts ~/.openclaw/hooks/promptdome-gate/\n\n# Plugin (explicit tool)\nmkdir -p ~/.openclaw/extensions/promptdome\ncp skills/promptdome/plugin/index.ts ~/.openclaw/extensions/promptdome/"
      },
      {
        "title": "2. Set API key",
        "body": "Add to ~/.openclaw/openclaw.json:\n\n{\n  \"env\": {\n    \"PROMPTDOME_API_KEY\": \"sk_shield_live_YOUR_KEY\"\n  }\n}\n\nOr set PROMPTDOME_API_KEY in your shell environment."
      },
      {
        "title": "3. Enable hook and restart",
        "body": "openclaw hooks enable promptdome-gate\nopenclaw gateway restart"
      },
      {
        "title": "What Happens After Install",
        "body": "Every incoming message → scanned automatically before the model processes it\nBLOCK (score ≥ 70): [PROMPTDOME BLOCK] warning injected into conversation\nWARN (score ≥ 40): Soft caution note injected\nALLOW: Silent — no overhead in conversation history\nScan log: ~/.openclaw/logs/promptdome-gate.log\nFail-open: if API is unreachable, messages pass through unblocked"
      },
      {
        "title": "Using the Agent Tool",
        "body": "Enable promptdome_scan in your agent's tool allowlist:\n\n{\n  \"agents\": {\n    \"list\": [{ \"id\": \"main\", \"tools\": { \"allow\": [\"promptdome_scan\"] } }]\n  }\n}\n\nThen agents call it like any tool — before processing web fetches, search results, uploaded files, or any external content."
      },
      {
        "title": "Self-Hosted PromptDome",
        "body": "Override the API endpoint:\n\n{\n  \"env\": {\n    \"PROMPTDOME_API_KEY\": \"sk_shield_live_...\",\n    \"PROMPTDOME_API_URL\": \"https://your-instance.com/api/v1/shield\"\n  }\n}"
      },
      {
        "title": "Detection Coverage",
        "body": "PromptDome engine covers 32 attack categories including:\n\nPrompt injection & jailbreaks\nFake system events / gateway spoofing\nPII & credential exfiltration\nClickFix / social engineering\nHTML/DOM injection (browser agents)\nAgentic chain poisoning\nMultilingual evasion (18 languages)\n\nFull category list: https://promptdome.cyberforge.one/docs"
      }
    ],
    "body": "PromptDome × OpenClaw\n\nAPI key required — Get yours free at https://promptdome.cyberforge.one/dashboard/api-keys (Sign up → Dashboard → API Keys → Create Key)\n\nAdds automatic prompt injection detection to any OpenClaw agent. Two components work together:\n\nComponent\tWhat it does\tWhen it fires\npromptdome-gate hook\tAuto-scans every incoming message; injects ⚠️ warning if injection detected\tEvery message:received — zero agent code required\npromptdome_scan tool\tExplicit scan agent can call on any content\tOn demand — web content, files, tool outputs\nQuick Setup (60 seconds)\nbash skills/promptdome/scripts/setup.sh --api-key sk_shield_live_YOUR_KEY\n\n\nThat's it. The script:\n\nTests your API key against the PromptDome API\nInstalls promptdome-gate hook → ~/.openclaw/hooks/promptdome-gate/\nInstalls promptdome_scan plugin → ~/.openclaw/extensions/promptdome/\nSaves API key to openclaw.json env block\nEnables the hook automatically\nPrompts you to restart the gateway\n\nGet an API key: https://promptdome.cyberforge.one/dashboard/api-keys\n\nManual Setup\n1. Copy files\n# Hook (auto-scanning)\nmkdir -p ~/.openclaw/hooks/promptdome-gate\ncp skills/promptdome/hook/HOOK.md   ~/.openclaw/hooks/promptdome-gate/\ncp skills/promptdome/hook/handler.ts ~/.openclaw/hooks/promptdome-gate/\n\n# Plugin (explicit tool)\nmkdir -p ~/.openclaw/extensions/promptdome\ncp skills/promptdome/plugin/index.ts ~/.openclaw/extensions/promptdome/\n\n2. Set API key\n\nAdd to ~/.openclaw/openclaw.json:\n\n{\n  \"env\": {\n    \"PROMPTDOME_API_KEY\": \"sk_shield_live_YOUR_KEY\"\n  }\n}\n\n\nOr set PROMPTDOME_API_KEY in your shell environment.\n\n3. Enable hook and restart\nopenclaw hooks enable promptdome-gate\nopenclaw gateway restart\n\nWhat Happens After Install\nEvery incoming message → scanned automatically before the model processes it\nBLOCK (score ≥ 70): [PROMPTDOME BLOCK] warning injected into conversation\nWARN (score ≥ 40): Soft caution note injected\nALLOW: Silent — no overhead in conversation history\nScan log: ~/.openclaw/logs/promptdome-gate.log\nFail-open: if API is unreachable, messages pass through unblocked\nUsing the Agent Tool\n\nEnable promptdome_scan in your agent's tool allowlist:\n\n{\n  \"agents\": {\n    \"list\": [{ \"id\": \"main\", \"tools\": { \"allow\": [\"promptdome_scan\"] } }]\n  }\n}\n\n\nThen agents call it like any tool — before processing web fetches, search results, uploaded files, or any external content.\n\nSelf-Hosted PromptDome\n\nOverride the API endpoint:\n\n{\n  \"env\": {\n    \"PROMPTDOME_API_KEY\": \"sk_shield_live_...\",\n    \"PROMPTDOME_API_URL\": \"https://your-instance.com/api/v1/shield\"\n  }\n}\n\nDetection Coverage\n\nPromptDome engine covers 32 attack categories including:\n\nPrompt injection & jailbreaks\nFake system events / gateway spoofing\nPII & credential exfiltration\nClickFix / social engineering\nHTML/DOM injection (browser agents)\nAgentic chain poisoning\nMultilingual evasion (18 languages)\n\nFull category list: https://promptdome.cyberforge.one/docs"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/tschew72/promptdome",
    "publisherUrl": "https://clawhub.ai/tschew72/promptdome",
    "owner": "tschew72",
    "version": "1.3.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/promptdome",
    "downloadUrl": "https://openagent3.xyz/downloads/promptdome",
    "agentUrl": "https://openagent3.xyz/skills/promptdome/agent",
    "manifestUrl": "https://openagent3.xyz/skills/promptdome/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/promptdome/agent.md"
  }
}