Security audit tool for ClawHub/OpenClaw skills (static analysis + reputation scoring)

What to consider before installing or running this skill: - The package materials conflict: SKILL.md declares VirusTotal integration and an API key, but the included script only does local static pattern scanning. Ask the author to explain the mismatch and provide source for any network/sandbox components before trusting external features. - Do not supply a VIRUSTOTAL_API_KEY or other secrets unless you confirm the tool actually uses that API and you trust the author. Right now the key is unnecessary according to the code. - The tool auto-whitelists itself (SELF_WHITELIST = ['claw-secure-auditor']), so its own self-audit will always be marked Safe. Do not rely solely on this tool's results to make security decisions—perform independent/manual review or use multiple scanners. - If you want to run it: inspect the Python file yourself or run it in a disposable environment (container or VM) on a non-sensitive copy of the target skill. That ensures the code does what you expect and can't access real credentials. - Recommended next steps before trusting the skill: request an authoritative source URL and release (the homepage shows a placeholder), request clarity on whether VirusTotal/sandbox features exist and provide code for them, and confirm why registry metadata differs from SKILL.md. If the author cannot justify the discrepancies, treat the tool as untrusted.

Type: OpenClaw Skill Name: claw-secure-auditor Version: 1.1.1 The OpenClaw Secure Auditor skill bundle is classified as benign. Its primary function is static analysis of other skills, searching for dangerous patterns like shell execution, file deletion, credential exposure, and prompt injection keywords. The `auditor.py` script correctly implements this read-only scanning functionality without executing any of the detected patterns, modifying files, or exfiltrating data. Although `SKILL.md` mentions a `VIRUSTOTAL_API_KEY` and 'reputation scoring' implying external API calls, the provided Python script does not actually utilize this key or make any network requests, which is a functional discrepancy but not indicative of malicious intent. There is no evidence of prompt injection against the agent, obfuscation, or persistence mechanisms.