Browse / Unsafe Model Loading and Supply Chain / AIID-1368
Malicious OpenClaw Skills Reportedly Delivered AMOS Stealer and Exfiltrated Credentials via ClawHub
- Class
- Unsafe Model Loading and Supply Chain (filed by a model that read the source)
- Technique
- Real-world incidents
- Affected
- Malicious Actors, Openclaw (incident)
What happened, in short
Malicious OpenClaw skills posing as utilities ran obfuscated commands, fetched payloads, delivered AMOS Stealer on macOS, and exfiltrated private keys and API tokens from users. (Our summary, written by a model. The source text is below.)
Details
Bitdefender researchers reported abuse in OpenClaw's third-party 'skills' ecosystem. In a Feb. 2026 sample, about 17% of skills were reportedly assessed as malicious, with many seemingly cloned under slight name changes. Posing as utilities, some skills were reportedly found to run obfuscated commands, fetch remote payloads, and in some cases deliver AMOS Stealer on macOS. Other skills were reportedly observed searching for private keys or API tokens and exfiltrating them.
References
Source: AI Incident Database, used under CC BY-SA 4.0.