{
  "schemaVersion": "1.0",
  "item": {
    "slug": "agentgate-security",
    "name": "AgentGate - Enterprise Security Firewall for OpenClaw",
    "source": "tencent",
    "type": "skill",
    "category": "安全合规",
    "sourceUrl": "https://clawhub.ai/wiserautomation/agentgate-security",
    "canonicalUrl": "https://clawhub.ai/wiserautomation/agentgate-security",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/agentgate-security",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agentgate-security",
    "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",
      "slug": "agentgate-security",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T22:35:12.477Z",
      "expiresAt": "2026-04-30T22:35:12.477Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agentgate-security",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agentgate-security",
        "contentDisposition": "attachment; filename=\"agentgate-security-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "agentgate-security"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/agentgate-security"
    },
    "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/agentgate-security",
    "agentPageUrl": "https://openagent3.xyz/skills/agentgate-security/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agentgate-security/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agentgate-security/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": "AgentGate - Enterprise Security Firewall for OpenClaw",
        "body": "AgentGate is a real-time policy enforcement layer that intercepts every tool call your OpenClaw agent makes before it executes. It evaluates the call against human-defined regex-based rules stored in Firestore and returns one of three decisions: ALLOW, DENY, or REQUIRE_APPROVAL."
      },
      {
        "title": "Why this exists",
        "body": "OpenClaw agents operate with full tool access by default. A single hallucination can cause the agent to run rm -rf, send unauthorized emails, issue Stripe API calls, push broken code to production, or exfiltrate data to external endpoints. AgentGate intercepts every tool call before execution."
      },
      {
        "title": "Architecture",
        "body": "AgentGate wraps the agent executeTool method using a middleware pattern. On every tool invocation it sends a POST request to the AgentGate Firebase Cloud Function with the agent API key, tool name, and serialized arguments. The function validates the key, evaluates regex policies, writes to the audit log, and returns the decision in under 80ms."
      },
      {
        "title": "Decision types",
        "body": "ALLOW: Tool executes normally.\nDENY: Tool is blocked. Agent receives structured error: \"AgentGate: Action blocked by policy [policy_id]. Do not retry.\"\nREQUIRE_APPROVAL: Execution paused. Telegram webhook fires to operator with Approve/Deny buttons. Agent polls Firestore every 2 seconds for up to 5 minutes."
      },
      {
        "title": "Supported tool types",
        "body": "bash: shell command execution\nbrowser: Playwright-based web automation\nfetch: outbound HTTP requests\nfs: filesystem read and write\nemail: SMTP and SendGrid integrations\nstripe: payment API calls"
      },
      {
        "title": "Policy format",
        "body": "agentId: string\ntoolName: string (e.g. \"bash\")\ncondition: string (regex evaluated against JSON.stringify(args))\nruleType: \"ALLOW\" | \"DENY\" | \"REQUIRE_APPROVAL\"\npriority: integer (lower = evaluated first)\n\nExample - block destructive bash commands:\ntoolName: \"bash\"\ncondition: \"rm\\s+-rf|DROP\\s+TABLE\"\nruleType: \"DENY\"\n\nExample - require approval for Stripe charges over $100:\ntoolName: \"stripe\"\ncondition: \"\"amount\":\\s*[1-9][0-9]{4,}\"\nruleType: \"REQUIRE_APPROVAL\"\n\nExample - whitelist-only outbound fetch:\ntoolName: \"fetch\"\ncondition: \"^(?!.(api\\.github\\.com|agent-gate-rho\\.vercel\\.app)).$\"\nruleType: \"DENY\""
      },
      {
        "title": "SDK usage",
        "body": "npm install @agentgate/openclaw-guard\n\nimport OpenClaw from 'openclaw';\nimport { withAgentGate } from '@agentgate/openclaw-guard';\n\nconst agent = new OpenClaw({ model: 'claude-3-5-sonnet', tools: ['bash', 'browser', 'fetch'] });\n\nconst securedAgent = withAgentGate(agent, {\napiKey: process.env.AGENTGATE_API_KEY,\nendpoint: 'https://agent-gate-rho.vercel.app/api/evaluate-action',\nonDeny: (toolName, args, policyId) => console.log('Blocked:', toolName, policyId),\nonApprovalRequired: (toolName, args) => console.log('Awaiting approval:', toolName)\n});\n\nawait securedAgent.run('Research competitors and update the CRM');"
      },
      {
        "title": "Dashboard",
        "body": "https://agent-gate-rho.vercel.app provides:\n\nAgent management and API key rotation\nAI Policy Wizard: describe rules in plain English, Gemini generates the regex\nReal-time audit log via Firestore onSnapshot\nApproval queue with one-click approve or deny"
      },
      {
        "title": "Getting started",
        "body": "Sign up free at https://agent-gate-rho.vercel.app\nCreate an agent and copy the API key\nnpm install @agentgate/openclaw-guard\nWrap your agent with withAgentGate\nDefine policies in the dashboard using the AI Wizard\nWatch the real-time audit log as your agent runs"
      },
      {
        "title": "Pricing",
        "body": "Free: 1 agent, 500 evaluations/month, 7-day audit log. No credit card required."
      }
    ],
    "body": "AgentGate - Enterprise Security Firewall for OpenClaw\n\nAgentGate is a real-time policy enforcement layer that intercepts every tool call your OpenClaw agent makes before it executes. It evaluates the call against human-defined regex-based rules stored in Firestore and returns one of three decisions: ALLOW, DENY, or REQUIRE_APPROVAL.\n\nWhy this exists\n\nOpenClaw agents operate with full tool access by default. A single hallucination can cause the agent to run rm -rf, send unauthorized emails, issue Stripe API calls, push broken code to production, or exfiltrate data to external endpoints. AgentGate intercepts every tool call before execution.\n\nArchitecture\n\nAgentGate wraps the agent executeTool method using a middleware pattern. On every tool invocation it sends a POST request to the AgentGate Firebase Cloud Function with the agent API key, tool name, and serialized arguments. The function validates the key, evaluates regex policies, writes to the audit log, and returns the decision in under 80ms.\n\nDecision types\n\nALLOW: Tool executes normally. DENY: Tool is blocked. Agent receives structured error: \"AgentGate: Action blocked by policy [policy_id]. Do not retry.\" REQUIRE_APPROVAL: Execution paused. Telegram webhook fires to operator with Approve/Deny buttons. Agent polls Firestore every 2 seconds for up to 5 minutes.\n\nSupported tool types\nbash: shell command execution\nbrowser: Playwright-based web automation\nfetch: outbound HTTP requests\nfs: filesystem read and write\nemail: SMTP and SendGrid integrations\nstripe: payment API calls\nPolicy format\n\nagentId: string toolName: string (e.g. \"bash\") condition: string (regex evaluated against JSON.stringify(args)) ruleType: \"ALLOW\" | \"DENY\" | \"REQUIRE_APPROVAL\" priority: integer (lower = evaluated first)\n\nExample - block destructive bash commands: toolName: \"bash\" condition: \"rm\\s+-rf|DROP\\s+TABLE\" ruleType: \"DENY\"\n\nExample - require approval for Stripe charges over $100: toolName: \"stripe\" condition: \"\"amount\":\\s*[1-9][0-9]{4,}\" ruleType: \"REQUIRE_APPROVAL\"\n\nExample - whitelist-only outbound fetch: toolName: \"fetch\" condition: \"^(?!.(api\\.github\\.com|agent-gate-rho\\.vercel\\.app)).$\" ruleType: \"DENY\"\n\nSDK usage\n\nnpm install @agentgate/openclaw-guard\n\nimport OpenClaw from 'openclaw'; import { withAgentGate } from '@agentgate/openclaw-guard';\n\nconst agent = new OpenClaw({ model: 'claude-3-5-sonnet', tools: ['bash', 'browser', 'fetch'] });\n\nconst securedAgent = withAgentGate(agent, { apiKey: process.env.AGENTGATE_API_KEY, endpoint: 'https://agent-gate-rho.vercel.app/api/evaluate-action', onDeny: (toolName, args, policyId) => console.log('Blocked:', toolName, policyId), onApprovalRequired: (toolName, args) => console.log('Awaiting approval:', toolName) });\n\nawait securedAgent.run('Research competitors and update the CRM');\n\nDashboard\n\nhttps://agent-gate-rho.vercel.app provides:\n\nAgent management and API key rotation\nAI Policy Wizard: describe rules in plain English, Gemini generates the regex\nReal-time audit log via Firestore onSnapshot\nApproval queue with one-click approve or deny\nGetting started\nSign up free at https://agent-gate-rho.vercel.app\nCreate an agent and copy the API key\nnpm install @agentgate/openclaw-guard\nWrap your agent with withAgentGate\nDefine policies in the dashboard using the AI Wizard\nWatch the real-time audit log as your agent runs\nPricing\n\nFree: 1 agent, 500 evaluations/month, 7-day audit log. No credit card required."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/wiserautomation/agentgate-security",
    "publisherUrl": "https://clawhub.ai/wiserautomation/agentgate-security",
    "owner": "wiserautomation",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/agentgate-security",
    "downloadUrl": "https://openagent3.xyz/downloads/agentgate-security",
    "agentUrl": "https://openagent3.xyz/skills/agentgate-security/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agentgate-security/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agentgate-security/agent.md"
  }
}