leak-checkScan session logs for leaked credentials. Checks JSONL session files against known credential patterns and reports which AI provider received the data.
Install via ClawdBot CLI:
clawdbot install khaney64/leak-checkScan OpenClaw session JSONL files for leaked credentials. Reports which real AI provider (anthropic, openai, google, etc.) received the data, skipping internal delivery echoes.
# Check for leaked credentials (default: discord format)
node scripts/leak-check.js
# JSON output
node scripts/leak-check.js --format jsonCredentials to check are defined in leak-check.json. The script searches for this file in order:
./leak-check.json) ā for backward compatibility~/.openclaw/credentials/leak-check.json ā recommended persistent location (survives skill updates via clawhub)Since clawhub clears the skill directory on updates, place your config in ~/.openclaw/credentials/ to avoid losing it:
mkdir -p ~/.openclaw/credentials
cp leak-check.json ~/.openclaw/credentials/leak-check.jsonYou can also specify an explicit path with --config.
[
{ "name": "Discord", "search": "abc*xyz" },
{ "name": "Postmark", "search": "k7Qm9x" }
]Important: Do not store full credentials in this file. Use only a partial fragment ā enough to uniquely identify the credential via a contains, begins-with, or ends-with match.
Wildcard patterns:
abc* ā starts with "abc"*xyz ā ends with "xyz"abc*xyz ā starts with "abc" AND ends with "xyz"abc (no asterisk) ā contains "abc""" (empty) ā skip this credential--format ā Output format: discord (default) or json--config ā Path to credential config file (default: ./leak-check.json, then ~/.openclaw/credentials/leak-check.json)--help, -h ā Show help messageš **Credential Leak Check**
ā ļø **2 leaked credentials found**
**Discord Token**
ā¢ Session: `abc12345` | 2026-02-14 18:30 UTC | Provider: anthropic
**Postmark**
ā¢ Session: `def67890` | 2026-02-10 09:15 UTC | Provider: anthropicOr if clean:
š **Credential Leak Check**
ā
No leaked credentials found (checked 370 files, 7 credentials)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:
š **3 possible config echoes** (session contains leak-check config)
ā¢ **Discord**: 1 session
...
ā
No credential leaks beyond config echoesConfig 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/:
rm ~/.openclaw/agents/main/sessions/<session-uuid>.jsonlTip: Avoid reading or referencing leak-check.json during an OpenClaw session. If it happens, note the session ID from the report and delete it.
{
"leaks": [
{
"credential": "Discord Token",
"session": "abc12345",
"timestamp": "2026-02-14T18:30:00.000Z",
"provider": "anthropic"
}
],
"configEchoes": [
{
"credential": "Gateway",
"session": "b175e53c",
"timestamp": "2026-02-19T18:00:30.067Z",
"provider": "minimax-portal",
"configEcho": true
}
],
"summary": {
"filesScanned": 370,
"credentialsChecked": 7,
"leaksFound": 2,
"configEchoesFound": 1
}
}Generated Mar 1, 2026
AI development teams use this skill to regularly scan session logs for accidental credential leaks during testing and debugging of AI agents. It helps identify which AI provider (e.g., OpenAI, Anthropic) received sensitive data, enabling quick remediation and preventing security breaches in development environments.
Financial institutions deploy this skill to audit AI-powered customer service or trading bots for credential leaks, ensuring compliance with regulations like GDPR or PCI-DSS. It reports leaks to specific providers, allowing teams to trace incidents and implement corrective measures without storing full credentials in logs.
Healthcare organizations use the skill to monitor AI systems handling patient data for credential exposures, such as API keys for medical databases. By detecting leaks to providers like Google or Anthropic, it supports HIPAA compliance and safeguards sensitive health information from unauthorized access.
E-commerce platforms integrate this skill to scan logs from AI chatbots or recommendation engines for leaked payment gateway or shipping API credentials. It identifies leaks to providers like OpenAI, helping prevent fraud and maintain customer trust by securing transactional data.
Universities and online learning platforms use the skill to audit AI tutoring or administrative bots for credential leaks, such as student database access keys. Reporting leaks to specific providers enables IT teams to secure educational data and comply with privacy policies like FERPA.
Offer this skill as part of a subscription-based security monitoring service for AI developers, providing regular leak scans and alerts. Revenue comes from monthly or annual fees, with tiers based on scan frequency, number of credentials monitored, and integration support.
Provide consulting services to help businesses integrate and customize the skill for their specific AI environments, such as adding custom credential patterns or compliance reporting. Revenue is generated through project-based fees and ongoing maintenance contracts.
Distribute the skill as a free open-source tool with basic leak scanning, while offering premium features like advanced analytics, real-time alerts, or multi-agent support for a fee. Revenue comes from upgrades and enterprise licenses.
š¬ Integration Tip
Place the leak-check.json config file in ~/.openclaw/credentials/ to persist across skill updates, and avoid referencing it during sessions to prevent config echoes in logs.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Perform a comprehensive read-only security audit of Clawdbot's own configuration. This is a knowledge-based skill that teaches Clawdbot to identify hardening opportunities across the system. Use when user asks to "run security check", "audit clawdbot", "check security hardening", or "what vulnerabilities does my Clawdbot have". This skill uses Clawdbot's internal capabilities and file system access to inspect configuration, detect misconfigurations, and recommend remediations. It is designed to be extensible - new checks can be added by updating this skill's knowledge.
Use when reviewing code for security vulnerabilities, implementing authentication flows, auditing OWASP Top 10, configuring CORS/CSP headers, handling secrets, input validation, SQL injection prevention, XSS protection, or any security-related code review.
Security check for ClawHub skills powered by Koi. Query the Clawdex API before installing any skill to verify it's safe.
Scan Clawdbot and MCP skills for malware, spyware, crypto-miners, and malicious code patterns before you install them. Security audit tool that detects data exfiltration, system modification attempts, backdoors, and obfuscation techniques.