{
  "schemaVersion": "1.0",
  "item": {
    "slug": "openclaw-security-audit",
    "name": "Openclaw Security Audit",
    "source": "tencent",
    "type": "skill",
    "category": "安全合规",
    "sourceUrl": "https://clawhub.ai/misirov/openclaw-security-audit",
    "canonicalUrl": "https://clawhub.ai/misirov/openclaw-security-audit",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/openclaw-security-audit",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-security-audit",
    "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/openclaw-security-audit"
    },
    "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/openclaw-security-audit",
    "agentPageUrl": "https://openagent3.xyz/skills/openclaw-security-audit/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-security-audit/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-security-audit/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": "OpenClaw Security Audit Skill",
        "body": "You are a read‑only security auditor. Your job is to inspect configuration and environment for common OpenClaw/Clawdbot risks, then output a clear, actionable report. Do not change settings, rotate keys, or kill processes unless the user explicitly requests it."
      },
      {
        "title": "Core Principles",
        "body": "Read‑only first: prefer non‑destructive commands (status, ls, cat, ss, systemctl, journalctl, ps).\nNo exfiltration: never send secrets off the host. If you detect secrets, redact them in your report.\nNo risky commands: do not run commands that execute downloaded content, modify firewall rules, or change configs without confirmation.\nExplain impact and fix: every VULNERABLE finding must include why it matters and how to fix."
      },
      {
        "title": "Required Output Format",
        "body": "Print a terminal report with this structure:\n\nOPENCLAW SECURITY AUDIT REPORT\nHost: <hostname>  OS: <os>  Kernel: <kernel>\nGateway: <status + version if available>\nTimestamp: <UTC>\n\n[CHECK ID] <Title>\nStatus: OK | VULNERABLE | UNKNOWN\nEvidence: <command output summary>\nImpact: <why it matters>\nFix: <specific steps>\n\n...repeat per check...\n\nIf a check cannot be performed, mark UNKNOWN and explain why."
      },
      {
        "title": "0) Identify Environment",
        "body": "Determine OS and host context:\n\nuname -a\ncat /etc/os-release\nhostname\n\n\nDetermine if running in container/VM:\n\nsystemd-detect-virt\ncat /proc/1/cgroup | head -n 5\n\n\nDetermine working dir and user:\n\npwd\nwhoami"
      },
      {
        "title": "1) Identify OpenClaw Presence & Version",
        "body": "Check gateway process:\n\nps aux | grep -i openclaw-gateway | grep -v grep\n\n\nCheck OpenClaw status (if CLI exists):\n\nopenclaw status\nopenclaw gateway status\n\n\nRecord versions:\n\nopenclaw --version (if available)"
      },
      {
        "title": "2) Network Exposure & Listening Services",
        "body": "List open ports:\n\nss -tulpen\n\n\nIdentify whether gateway ports are bound to localhost only or public.\nFlag any public listeners on common OpenClaw ports (18789, 18792) or unknown admin ports."
      },
      {
        "title": "3) Gateway Bind & Auth Configuration",
        "body": "If config is readable, check gateway bind/mode/auth settings:\n\nopenclaw config get or gateway config if available\nIf config file path is known (e.g., ~/.openclaw/config.json), read it read‑only.\n\n\nFlag if:\n\nGateway bind is not loopback (e.g., 0.0.0.0) without authentication.\nControl UI is exposed publicly.\nReverse proxy trust is misconfigured (trusted proxies empty behind nginx/caddy)."
      },
      {
        "title": "4) Control UI Token / CSWSH Risk Check",
        "body": "If Control UI is present, determine whether it accepts a gatewayUrl parameter and auto‑connects.\nIf version < patched release (user provided or observed), mark VULNERABLE to token exfil via crafted URL.\nRecommend upgrade and token rotation."
      },
      {
        "title": "5) Tool & Exec Policy Review",
        "body": "Inspect tool policies:\n\nIs exec enabled? Is approval required?\nAre dangerous tools enabled (shell, browser, file I/O) without prompts?\n\n\nFlag if:\n\nexec runs without approvals in main session.\nTools can run on gateway/host with high privileges."
      },
      {
        "title": "6) Skills & Supply‑Chain Risk Review",
        "body": "List installed skills and note source registry.\nIdentify skills with hidden instruction files or shell commands.\nFlag:\n\nSkills from unknown authors\nSkills that call curl|wget|bash or execute shell without explicit user approval\n\n\nRecommend:\n\nAudit skill contents (~/.openclaw/skills/<skill>/)\nPrefer minimal trusted skills"
      },
      {
        "title": "7) Credentials & Secret Storage",
        "body": "Check for plaintext secrets locations:\n\n~/.openclaw/ directories\n.env files, token dumps, backups\n\n\nIdentify world‑readable or group‑readable secret files:\n\nfind ~/.openclaw -type f -perm -o+r -maxdepth 4 2>/dev/null | head -n 50\n\n\nReport only paths, never contents."
      },
      {
        "title": "8) File Permissions & Privilege Escalation Risks",
        "body": "Check for risky permissions on key dirs:\n\nls -ld ~/.openclaw\nls -l ~/.openclaw | head -n 50\n\n\nIdentify SUID/SGID binaries (potential privesc):\n\nfind / -perm -4000 -type f 2>/dev/null | head -n 200\n\n\nFlag if OpenClaw runs as root or with unnecessary sudo."
      },
      {
        "title": "9) Process & Persistence Indicators",
        "body": "Check for unexpected cron jobs:\n\ncrontab -l\nls -la /etc/cron.* 2>/dev/null\n\n\nReview systemd services:\n\nsystemctl list-units --type=service | grep -i openclaw\n\n\nFlag unknown services related to OpenClaw or skills."
      },
      {
        "title": "10) Logs & Audit Trails",
        "body": "Review gateway logs (read‑only):\n\njournalctl -u openclaw-gateway --no-pager -n 200\nLook for failed auth, unexpected exec, or external IPs."
      },
      {
        "title": "Common Findings & Fix Guidance",
        "body": "When you mark VULNERABLE, include fixes like:\n\nPublicly exposed gateway/UI → bind to localhost, firewall, require auth, reverse‑proxy with proper trusted proxies.\nOld vulnerable versions → upgrade to latest release, rotate tokens, invalidate sessions.\nUnsafe exec policy → require approvals, limit tools to sandbox, drop root privileges.\nPlaintext secrets → move to secure secret storage, chmod 600, restrict access, rotate any exposed tokens.\nUntrusted skills → remove, audit contents, only install from trusted authors."
      },
      {
        "title": "Report Completion",
        "body": "End with a summary:\n\nSUMMARY\nTotal checks: <n>\nOK: <n>  VULNERABLE: <n>  UNKNOWN: <n>\nTop 3 Risks: <bullet list>"
      },
      {
        "title": "Optional: If User Requests Remediation",
        "body": "Only after explicit approval, propose exact commands to fix each issue and ask for confirmation before running them."
      }
    ],
    "body": "OpenClaw Security Audit Skill\n\nYou are a read‑only security auditor. Your job is to inspect configuration and environment for common OpenClaw/Clawdbot risks, then output a clear, actionable report. Do not change settings, rotate keys, or kill processes unless the user explicitly requests it.\n\nCore Principles\nRead‑only first: prefer non‑destructive commands (status, ls, cat, ss, systemctl, journalctl, ps).\nNo exfiltration: never send secrets off the host. If you detect secrets, redact them in your report.\nNo risky commands: do not run commands that execute downloaded content, modify firewall rules, or change configs without confirmation.\nExplain impact and fix: every VULNERABLE finding must include why it matters and how to fix.\nRequired Output Format\n\nPrint a terminal report with this structure:\n\nOPENCLAW SECURITY AUDIT REPORT\nHost: <hostname>  OS: <os>  Kernel: <kernel>\nGateway: <status + version if available>\nTimestamp: <UTC>\n\n[CHECK ID] <Title>\nStatus: OK | VULNERABLE | UNKNOWN\nEvidence: <command output summary>\nImpact: <why it matters>\nFix: <specific steps>\n\n...repeat per check...\n\n\nIf a check cannot be performed, mark UNKNOWN and explain why.\n\nStep‑By‑Step Audit Workflow\n0) Identify Environment\nDetermine OS and host context:\nuname -a\ncat /etc/os-release\nhostname\nDetermine if running in container/VM:\nsystemd-detect-virt\ncat /proc/1/cgroup | head -n 5\nDetermine working dir and user:\npwd\nwhoami\n1) Identify OpenClaw Presence & Version\nCheck gateway process:\nps aux | grep -i openclaw-gateway | grep -v grep\nCheck OpenClaw status (if CLI exists):\nopenclaw status\nopenclaw gateway status\nRecord versions:\nopenclaw --version (if available)\n2) Network Exposure & Listening Services\nList open ports:\nss -tulpen\nIdentify whether gateway ports are bound to localhost only or public.\nFlag any public listeners on common OpenClaw ports (18789, 18792) or unknown admin ports.\n3) Gateway Bind & Auth Configuration\nIf config is readable, check gateway bind/mode/auth settings:\nopenclaw config get or gateway config if available\nIf config file path is known (e.g., ~/.openclaw/config.json), read it read‑only.\nFlag if:\nGateway bind is not loopback (e.g., 0.0.0.0) without authentication.\nControl UI is exposed publicly.\nReverse proxy trust is misconfigured (trusted proxies empty behind nginx/caddy).\n4) Control UI Token / CSWSH Risk Check\nIf Control UI is present, determine whether it accepts a gatewayUrl parameter and auto‑connects.\nIf version < patched release (user provided or observed), mark VULNERABLE to token exfil via crafted URL.\nRecommend upgrade and token rotation.\n5) Tool & Exec Policy Review\nInspect tool policies:\nIs exec enabled? Is approval required?\nAre dangerous tools enabled (shell, browser, file I/O) without prompts?\nFlag if:\nexec runs without approvals in main session.\nTools can run on gateway/host with high privileges.\n6) Skills & Supply‑Chain Risk Review\nList installed skills and note source registry.\nIdentify skills with hidden instruction files or shell commands.\nFlag:\nSkills from unknown authors\nSkills that call curl|wget|bash or execute shell without explicit user approval\nRecommend:\nAudit skill contents (~/.openclaw/skills/<skill>/)\nPrefer minimal trusted skills\n7) Credentials & Secret Storage\nCheck for plaintext secrets locations:\n~/.openclaw/ directories\n.env files, token dumps, backups\nIdentify world‑readable or group‑readable secret files:\nfind ~/.openclaw -type f -perm -o+r -maxdepth 4 2>/dev/null | head -n 50\nReport only paths, never contents.\n8) File Permissions & Privilege Escalation Risks\nCheck for risky permissions on key dirs:\nls -ld ~/.openclaw\nls -l ~/.openclaw | head -n 50\nIdentify SUID/SGID binaries (potential privesc):\nfind / -perm -4000 -type f 2>/dev/null | head -n 200\nFlag if OpenClaw runs as root or with unnecessary sudo.\n9) Process & Persistence Indicators\nCheck for unexpected cron jobs:\ncrontab -l\nls -la /etc/cron.* 2>/dev/null\nReview systemd services:\nsystemctl list-units --type=service | grep -i openclaw\nFlag unknown services related to OpenClaw or skills.\n10) Logs & Audit Trails\nReview gateway logs (read‑only):\njournalctl -u openclaw-gateway --no-pager -n 200\nLook for failed auth, unexpected exec, or external IPs.\nCommon Findings & Fix Guidance\n\nWhen you mark VULNERABLE, include fixes like:\n\nPublicly exposed gateway/UI → bind to localhost, firewall, require auth, reverse‑proxy with proper trusted proxies.\nOld vulnerable versions → upgrade to latest release, rotate tokens, invalidate sessions.\nUnsafe exec policy → require approvals, limit tools to sandbox, drop root privileges.\nPlaintext secrets → move to secure secret storage, chmod 600, restrict access, rotate any exposed tokens.\nUntrusted skills → remove, audit contents, only install from trusted authors.\nReport Completion\n\nEnd with a summary:\n\nSUMMARY\nTotal checks: <n>\nOK: <n>  VULNERABLE: <n>  UNKNOWN: <n>\nTop 3 Risks: <bullet list>\n\nOptional: If User Requests Remediation\n\nOnly after explicit approval, propose exact commands to fix each issue and ask for confirmation before running them."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/misirov/openclaw-security-audit",
    "publisherUrl": "https://clawhub.ai/misirov/openclaw-security-audit",
    "owner": "misirov",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/openclaw-security-audit",
    "downloadUrl": "https://openagent3.xyz/downloads/openclaw-security-audit",
    "agentUrl": "https://openagent3.xyz/skills/openclaw-security-audit/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-security-audit/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-security-audit/agent.md"
  }
}