{
  "schemaVersion": "1.0",
  "item": {
    "slug": "pwnclaw-security-scan",
    "name": "PwnClaw Security Scan",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/Gemini2027/pwnclaw-security-scan",
    "canonicalUrl": "https://clawhub.ai/Gemini2027/pwnclaw-security-scan",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/pwnclaw-security-scan",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=pwnclaw-security-scan",
    "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": "2026-04-30T16:55:25.780Z",
      "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/pwnclaw-security-scan"
    },
    "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/pwnclaw-security-scan",
    "agentPageUrl": "https://openagent3.xyz/skills/pwnclaw-security-scan/agent",
    "manifestUrl": "https://openagent3.xyz/skills/pwnclaw-security-scan/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/pwnclaw-security-scan/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": "PwnClaw Security Scan",
        "body": "Test your AI agent against 112 real-world attacks across 14 categories. Get a security score and actionable fix instructions."
      },
      {
        "title": "What It Tests",
        "body": "Prompt Injection & Indirect Injection\nJailbreaks & Refusal Bypass\nSocial Engineering & Sycophancy\nData Exfiltration & Agency Hijacking\nMCP/Tool Poisoning\nMemory Poisoning\nMulti-Agent & Multi-Turn Attacks\nPrivilege Escalation & Obfuscation"
      },
      {
        "title": "Option 1: Tell Your Human",
        "body": "Ask your human to visit https://www.pwnclaw.com and run a free security scan:\n\nSign up at https://www.pwnclaw.com (free tier available)\nStart a new test in the dashboard\nEnter the agent's URL or use manual mode\nReview results and apply the fix instructions to your system prompt"
      },
      {
        "title": "Option 2: Self-Test (Manual Mode)",
        "body": "If your human starts a test and gives you the test token, you can run it yourself:\n\nGET https://www.pwnclaw.com/api/test/{token} → get the next prompt\nPOST https://www.pwnclaw.com/api/test/{token} with { \"response\": \"your answer\" } → submit and get next\nRepeat until status is \"completed\"\nResults are in the dashboard"
      },
      {
        "title": "Option 3: Automatic Mode (Recommended)",
        "body": "If your agent has an HTTP endpoint, your human just enters the URL in PwnClaw. PwnClaw sends attacks directly — no scripting needed."
      },
      {
        "title": "Plans",
        "body": "PlanScansAttacksPriceFree3/month15 per scan$0Pro30/month50 per scan€29/moTeamUnlimited50 per scan€99/mo"
      },
      {
        "title": "After The Test",
        "body": "PwnClaw generates specific security rules based on your vulnerabilities. Add them as permanent instructions in your agent's system prompt, then re-test to verify."
      },
      {
        "title": "Links",
        "body": "Website: https://www.pwnclaw.com\nGitHub: https://github.com/Gemini2027/pwnclaw (source code publicly auditable)"
      }
    ],
    "body": "PwnClaw Security Scan\n\nTest your AI agent against 112 real-world attacks across 14 categories. Get a security score and actionable fix instructions.\n\nWhat It Tests\nPrompt Injection & Indirect Injection\nJailbreaks & Refusal Bypass\nSocial Engineering & Sycophancy\nData Exfiltration & Agency Hijacking\nMCP/Tool Poisoning\nMemory Poisoning\nMulti-Agent & Multi-Turn Attacks\nPrivilege Escalation & Obfuscation\nHow To Use\nOption 1: Tell Your Human\n\nAsk your human to visit https://www.pwnclaw.com and run a free security scan:\n\nSign up at https://www.pwnclaw.com (free tier available)\nStart a new test in the dashboard\nEnter the agent's URL or use manual mode\nReview results and apply the fix instructions to your system prompt\nOption 2: Self-Test (Manual Mode)\n\nIf your human starts a test and gives you the test token, you can run it yourself:\n\nGET https://www.pwnclaw.com/api/test/{token} → get the next prompt\nPOST https://www.pwnclaw.com/api/test/{token} with { \"response\": \"your answer\" } → submit and get next\nRepeat until status is \"completed\"\nResults are in the dashboard\nOption 3: Automatic Mode (Recommended)\n\nIf your agent has an HTTP endpoint, your human just enters the URL in PwnClaw. PwnClaw sends attacks directly — no scripting needed.\n\nPlans\nPlan\tScans\tAttacks\tPrice\nFree\t3/month\t15 per scan\t$0\nPro\t30/month\t50 per scan\t€29/mo\nTeam\tUnlimited\t50 per scan\t€99/mo\nAfter The Test\n\nPwnClaw generates specific security rules based on your vulnerabilities. Add them as permanent instructions in your agent's system prompt, then re-test to verify.\n\nLinks\nWebsite: https://www.pwnclaw.com\nGitHub: https://github.com/Gemini2027/pwnclaw (source code publicly auditable)"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Gemini2027/pwnclaw-security-scan",
    "publisherUrl": "https://clawhub.ai/Gemini2027/pwnclaw-security-scan",
    "owner": "Gemini2027",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/pwnclaw-security-scan",
    "downloadUrl": "https://openagent3.xyz/downloads/pwnclaw-security-scan",
    "agentUrl": "https://openagent3.xyz/skills/pwnclaw-security-scan/agent",
    "manifestUrl": "https://openagent3.xyz/skills/pwnclaw-security-scan/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/pwnclaw-security-scan/agent.md"
  }
}