Malicious OpenClaw Skills Reportedly Delivered AMOS Stealer and Exfiltrated Credentials via ClawHub

February 1, 2026

Bitdefender researchers uncovered abuse in OpenClaw's third-party 'skills' ecosystem, revealing a malicious 17% of skills. The compromised skills were found to pose as utilities, run obfuscated commands, fetch remote payloads, deliver AMOS Stealer on macOS, and exfiltrate private keys or API tokens via ClawHub. This incident highlights the need for responsible AI governance and guardrails to prevent similar harm.

Matched TAIM controls

Suggested mapping from embedding similarity (not a formal assessment). Browse all TAIM controls

Alleged deployer
Unknown threat actors distributing malicious OpenClaw skills, Unknown threat actors, Malicious actors
Alleged developer
OpenClaw, Malicious actors
Alleged harmed parties
Privacy, Organizations using OpenClaw, OpenClaw users

AI governance case studies

For forensic AI governance failure analysis (TAIMScore™ case studies), browse Human Signal’s Failure Files™.

Source

Data from the AI Incident Database (AIID). Cite this incident: https://incidentdatabase.ai/cite/1368

Data source

Incident data is from the AI Incident Database (AIID).

When citing the database as a whole, please use:

McGregor, S. (2021) Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database. In Proceedings of the Thirty-Third Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-21). Virtual Conference.

Pre-print on arXiv · Database snapshots & citation guide

We use weekly snapshots of the AIID for stable reference. For the official suggested citation of a specific incident, use the “Cite this incident” link on each incident page.