secure-openclaw-ai-assistant
Warn
Audited by Socket on Sep 12, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s purpose broadly matches its capabilities, but its footprint is disproportionate for a messaging assistant. It combines full local tool access, persistent memory, remote deployment, public messaging ingress, 500+ external app actions, and multiple pipe-to-shell installers from different vendors. The main concern is high security risk from supply-chain trust and autonomous real-world integrations rather than confirmed malware or hidden exfiltration.
Confidence: 89%Severity: 78%
Audit Metadata