{
  "schemaVersion": "1.0",
  "item": {
    "slug": "leak-check",
    "name": "Leak Check",
    "source": "tencent",
    "type": "skill",
    "category": "数据分析",
    "sourceUrl": "https://clawhub.ai/khaney64/leak-check",
    "canonicalUrl": "https://clawhub.ai/khaney64/leak-check",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/leak-check",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=leak-check",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/leak-check.js"
    ],
    "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/leak-check"
    },
    "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/leak-check",
    "agentPageUrl": "https://openagent3.xyz/skills/leak-check/agent",
    "manifestUrl": "https://openagent3.xyz/skills/leak-check/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/leak-check/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": "Leak Check",
        "body": "Scan OpenClaw session JSONL files for leaked credentials. Reports which real AI provider (anthropic, openai, google, etc.) received the data, skipping internal delivery echoes."
      },
      {
        "title": "Quick Start",
        "body": "# Check for leaked credentials (default: discord format)\nnode scripts/leak-check.js\n\n# JSON output\nnode scripts/leak-check.js --format json"
      },
      {
        "title": "Configuration",
        "body": "Credentials to check are defined in leak-check.json. The script searches for this file in order:\n\nSkill directory (./leak-check.json) — for backward compatibility\n~/.openclaw/credentials/leak-check.json — recommended persistent location (survives skill updates via clawhub)\n\nSince clawhub clears the skill directory on updates, place your config in ~/.openclaw/credentials/ to avoid losing it:\n\nmkdir -p ~/.openclaw/credentials\ncp leak-check.json ~/.openclaw/credentials/leak-check.json\n\nYou can also specify an explicit path with --config.\n\n[\n  { \"name\": \"Discord\", \"search\": \"abc*xyz\" },\n  { \"name\": \"Postmark\", \"search\": \"k7Qm9x\" }\n]\n\nImportant: Do not store full credentials in this file. Use only a partial fragment — enough to uniquely identify the credential via a contains, begins-with, or ends-with match.\n\nWildcard patterns:\n\nabc* — starts with \"abc\"\n*xyz — ends with \"xyz\"\nabc*xyz — starts with \"abc\" AND ends with \"xyz\"\nabc (no asterisk) — contains \"abc\"\n\"\" (empty) — skip this credential"
      },
      {
        "title": "Options",
        "body": "--format <type> — Output format: discord (default) or json\n--config <path> — Path to credential config file (default: ./leak-check.json, then ~/.openclaw/credentials/leak-check.json)\n--help, -h — Show help message"
      },
      {
        "title": "Discord (Default)",
        "body": "🔐 **Credential Leak Check**\n\n⚠️ **2 leaked credentials found**\n\n**Discord Token**\n• Session: `abc12345` | 2026-02-14 18:30 UTC | Provider: anthropic\n\n**Postmark**\n• Session: `def67890` | 2026-02-10 09:15 UTC | Provider: anthropic\n\nOr if clean:\n\n🔐 **Credential Leak Check**\n✅ No leaked credentials found (checked 370 files, 7 credentials)"
      },
      {
        "title": "Config Echoes",
        "body": "If the leak-check.json config file is read or discussed during an OpenClaw session, the credential patterns will appear in that session's JSONL log. The scanner detects this and reports these matches separately as config echoes rather than real leaks:\n\n📋 **3 possible config echoes** (session contains leak-check config)\n\n• **Discord**: 1 session\n...\n\n✅ No credential leaks beyond config echoes\n\nConfig echoes will continue to appear on every run until the session file is removed. To clear them, delete the session file from ~/.openclaw/agents/main/sessions/:\n\nrm ~/.openclaw/agents/main/sessions/<session-uuid>.jsonl\n\nTip: Avoid reading or referencing leak-check.json during an OpenClaw session. If it happens, note the session ID from the report and delete it."
      },
      {
        "title": "JSON",
        "body": "{\n  \"leaks\": [\n    {\n      \"credential\": \"Discord Token\",\n      \"session\": \"abc12345\",\n      \"timestamp\": \"2026-02-14T18:30:00.000Z\",\n      \"provider\": \"anthropic\"\n    }\n  ],\n  \"configEchoes\": [\n    {\n      \"credential\": \"Gateway\",\n      \"session\": \"b175e53c\",\n      \"timestamp\": \"2026-02-19T18:00:30.067Z\",\n      \"provider\": \"minimax-portal\",\n      \"configEcho\": true\n    }\n  ],\n  \"summary\": {\n    \"filesScanned\": 370,\n    \"credentialsChecked\": 7,\n    \"leaksFound\": 2,\n    \"configEchoesFound\": 1\n  }\n}"
      },
      {
        "title": "Security",
        "body": "This skill is designed to be local-only and read-only. The following properties can be verified by inspecting scripts/leak-check.js:\n\nNo network access — no use of http, https, net, dgram, fetch, WebSocket, or any network API\nNo child processes — no use of child_process, exec, spawn, or execSync\nNo external dependencies — zero npm packages; only Node.js built-ins (fs, path, os)\nNo dynamic code execution — no eval(), Function(), or dynamic require()/import()\nNo file writes — only fs.readFileSync, fs.existsSync, and fs.readdirSync are used; no files are created, modified, or deleted\nNo environment variable access — does not read process.env\nOutput is stdout only — all results go to console.log; nothing is sent elsewhere"
      },
      {
        "title": "Verify It Yourself",
        "body": "Confirm no unexpected APIs are used anywhere in the script:\n\ngrep -E 'require\\(|import |http|fetch|net\\.|dgram|child_process|exec|spawn|eval\\(|Function\\(|\\.write|\\.unlink|\\.rename|process\\.env' scripts/leak-check.js\n\nExpected output — only the three built-in require() calls at the top of the file:\n\nconst fs = require('fs');\nconst path = require('path');\nconst os = require('os');"
      }
    ],
    "body": "Leak Check\n\nScan OpenClaw session JSONL files for leaked credentials. Reports which real AI provider (anthropic, openai, google, etc.) received the data, skipping internal delivery echoes.\n\nQuick Start\n# Check for leaked credentials (default: discord format)\nnode scripts/leak-check.js\n\n# JSON output\nnode scripts/leak-check.js --format json\n\nConfiguration\n\nCredentials to check are defined in leak-check.json. The script searches for this file in order:\n\nSkill directory (./leak-check.json) — for backward compatibility\n~/.openclaw/credentials/leak-check.json — recommended persistent location (survives skill updates via clawhub)\n\nSince clawhub clears the skill directory on updates, place your config in ~/.openclaw/credentials/ to avoid losing it:\n\nmkdir -p ~/.openclaw/credentials\ncp leak-check.json ~/.openclaw/credentials/leak-check.json\n\n\nYou can also specify an explicit path with --config.\n\n[\n  { \"name\": \"Discord\", \"search\": \"abc*xyz\" },\n  { \"name\": \"Postmark\", \"search\": \"k7Qm9x\" }\n]\n\n\nImportant: Do not store full credentials in this file. Use only a partial fragment — enough to uniquely identify the credential via a contains, begins-with, or ends-with match.\n\nWildcard patterns:\n\nabc* — starts with \"abc\"\n*xyz — ends with \"xyz\"\nabc*xyz — starts with \"abc\" AND ends with \"xyz\"\nabc (no asterisk) — contains \"abc\"\n\"\" (empty) — skip this credential\nOptions\n--format <type> — Output format: discord (default) or json\n--config <path> — Path to credential config file (default: ./leak-check.json, then ~/.openclaw/credentials/leak-check.json)\n--help, -h — Show help message\nOutput\nDiscord (Default)\n🔐 **Credential Leak Check**\n\n⚠️ **2 leaked credentials found**\n\n**Discord Token**\n• Session: `abc12345` | 2026-02-14 18:30 UTC | Provider: anthropic\n\n**Postmark**\n• Session: `def67890` | 2026-02-10 09:15 UTC | Provider: anthropic\n\n\nOr if clean:\n\n🔐 **Credential Leak Check**\n✅ No leaked credentials found (checked 370 files, 7 credentials)\n\nConfig Echoes\n\nIf the leak-check.json config file is read or discussed during an OpenClaw session, the credential patterns will appear in that session's JSONL log. The scanner detects this and reports these matches separately as config echoes rather than real leaks:\n\n📋 **3 possible config echoes** (session contains leak-check config)\n\n• **Discord**: 1 session\n...\n\n✅ No credential leaks beyond config echoes\n\n\nConfig echoes will continue to appear on every run until the session file is removed. To clear them, delete the session file from ~/.openclaw/agents/main/sessions/:\n\nrm ~/.openclaw/agents/main/sessions/<session-uuid>.jsonl\n\n\nTip: Avoid reading or referencing leak-check.json during an OpenClaw session. If it happens, note the session ID from the report and delete it.\n\nJSON\n{\n  \"leaks\": [\n    {\n      \"credential\": \"Discord Token\",\n      \"session\": \"abc12345\",\n      \"timestamp\": \"2026-02-14T18:30:00.000Z\",\n      \"provider\": \"anthropic\"\n    }\n  ],\n  \"configEchoes\": [\n    {\n      \"credential\": \"Gateway\",\n      \"session\": \"b175e53c\",\n      \"timestamp\": \"2026-02-19T18:00:30.067Z\",\n      \"provider\": \"minimax-portal\",\n      \"configEcho\": true\n    }\n  ],\n  \"summary\": {\n    \"filesScanned\": 370,\n    \"credentialsChecked\": 7,\n    \"leaksFound\": 2,\n    \"configEchoesFound\": 1\n  }\n}\n\nSecurity\n\nThis skill is designed to be local-only and read-only. The following properties can be verified by inspecting scripts/leak-check.js:\n\nNo network access — no use of http, https, net, dgram, fetch, WebSocket, or any network API\nNo child processes — no use of child_process, exec, spawn, or execSync\nNo external dependencies — zero npm packages; only Node.js built-ins (fs, path, os)\nNo dynamic code execution — no eval(), Function(), or dynamic require()/import()\nNo file writes — only fs.readFileSync, fs.existsSync, and fs.readdirSync are used; no files are created, modified, or deleted\nNo environment variable access — does not read process.env\nOutput is stdout only — all results go to console.log; nothing is sent elsewhere\nVerify It Yourself\n\nConfirm no unexpected APIs are used anywhere in the script:\n\ngrep -E 'require\\(|import |http|fetch|net\\.|dgram|child_process|exec|spawn|eval\\(|Function\\(|\\.write|\\.unlink|\\.rename|process\\.env' scripts/leak-check.js\n\n\nExpected output — only the three built-in require() calls at the top of the file:\n\nconst fs = require('fs');\nconst path = require('path');\nconst os = require('os');"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/khaney64/leak-check",
    "publisherUrl": "https://clawhub.ai/khaney64/leak-check",
    "owner": "khaney64",
    "version": "0.1.7",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/leak-check",
    "downloadUrl": "https://openagent3.xyz/downloads/leak-check",
    "agentUrl": "https://openagent3.xyz/skills/leak-check/agent",
    "manifestUrl": "https://openagent3.xyz/skills/leak-check/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/leak-check/agent.md"
  }
}