Security audit
Security checks for vulnerabilities and agentic risk
This is a local OpenClaw configuration audit tool; it reads potentially sensitive config data, but that access is disclosed, scoped to the audit purpose, and not paired with exfiltration or persistence.
Install only if you want a local audit of an OpenClaw configuration. The config and audit output may include sensitive paths, endpoint details, token lengths, or secret locations, so do not paste or share them publicly; use the sanitizer before sharing configs.
The skill claims to perform a comprehensive security audit, but the detected behavior indicates it mainly sanitizes or redacts secrets and does not actually validate security posture as described. This can create a false sense of safety, leading users to deploy insecure OpenClaw configurations under the mistaken belief that vulnerabilities and over-privileged agents were checked.
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
{ pattern: /\b[0-9]+:[A-Za-z0-9_-]{35,}\b/, type: 'Telegram bot token' },
{ pattern: /0x[a-fA-F0-9]{64}/i, type: 'Private key (hex 256-bit)' },
{ pattern: /xai-[a-zA-Z0-9]{20,}/i, type: 'xAI API key' },
{ pattern: /ghp_[a-zA-Z0-9]{36,}/i, type: 'GitHub personal access token' },
{ pattern: /gho_[a-zA-Z0-9]{36,}/i, type: 'GitHub OAuth token' },
{ pattern: /glpat-[a-zA-Z0-9_-]{20,}/i, type: 'GitLab personal access token' },
{ pattern: /AKIA[0-9A-Z]{16}/i, type: 'AWS access key' },
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
{ pattern: /\b[0-9]+:[A-Za-z0-9_-]{35,}\b/, type: 'Telegram bot token' },
{ pattern: /0x[a-fA-F0-9]{64}/i, type: 'Private key (hex 256-bit)' },
{ pattern: /xai-[a-zA-Z0-9]{20,}/i, type: 'xAI API key' },
{ pattern: /ghp_[a-zA-Z0-9]{36,}/i, type: 'GitHub personal access token' },
{ pattern: /gho_[a-zA-Z0-9]{36,}/i, type: 'GitHub OAuth token' },
{ pattern: /glpat-[a-zA-Z0-9_-]{20,}/i, type: 'GitLab personal access token' },
{ pattern: /AKIA[0-9A-Z]{16}/i, type: 'AWS access key' },
The skill advertises executable audit workflows that invoke local scripts and access environment-related capabilities, but it declares no explicit tool scope or permissions boundaries. In practice, this weakens least-privilege guarantees and can cause the agent framework to grant broader access than users expect when handling sensitive OpenClaw configurations and secrets.
The trigger language is broad enough to activate on generic security or hardening requests beyond the intended OpenClaw-config niche. Over-broad activation can cause the wrong skill to engage, prompting unnecessary file access or misleading security guidance in contexts it is not designed to handle.
The workflow instructs reading ~/.openclaw/openclaw.json directly, a file that may contain API keys, tokens, and other secrets, without warning the user or minimizing exposure. In a security-audit context this is especially risky because users may assume the process is safe while the skill encourages direct handling of highly sensitive local configuration data.
The README encourages auditing a live OpenClaw configuration file in a user home directory without warning that such files may contain secrets, tokens, network endpoints, and other sensitive operational data. In a security-audit tool, users are especially likely to share command output or the referenced file during troubleshooting, so the missing warning increases the chance of accidental secret disclosure.
This code converts the full configuration object to a JSON string as part of secret analysis, and the surrounding implementation inspects sensitive fields such as env values, bot tokens, and gateway tokens. While the skill's purpose is auditing, this file does not include any user-facing warning, prompt, or disclosure that sensitive configuration data will be processed in memory.
Detected: suspicious.dangerous_exec