Open Claw Integrates Virus Total Scanning to Detect Malicious Claw Hub Skills
Summary: OpenClaw has partnered with Google-owned VirusTotal to scan every skill uploaded to its ClawHub marketplace, hashing each bundle with SHA-256 and checking it against VirusTotal's database, then running unmatched bundles through VirusTotal Code Insight. Skills with a benign verdict are auto-approved, suspicious ones are flagged with a warning, malicious ones are blocked from download, and all active skills are re-scanned daily; OpenClaw cautioned the scanning is not a silver bullet and that concealed prompt injection payloads may still slip through.
Key Takeaway: The move follows reports of hundreds of malicious skills on ClawHub that posed as legitimate tools while exfiltrating data, injecting backdoors, or installing stealer malware - and OpenClaw's own maintainers concede scanning will not catch every concealed prompt injection. China's Ministry of Industry and Information Technology has already issued an alert about misconfigured OpenClaw instances, a signal that the exposure is being treated as a configuration and access problem rather than a reason to ban the tool.
Read the original at The Hacker News ↗
- Topics
- Detection & Response
- Related
- YARA-X 1.23.0 Release, (Sun, Nov 15th) Cyber Risks · Nov 15, 2026Inside Falcon AI Gateway: One Control Point for AI Traffic Cyber Risks · Nov 13, 2026Macfinger Click Fix campaign sends Down TheDRAIN infostealer for macOS, (Fri, Nov 13th) Cyber Risks · Nov 13, 2026