openhanako-personal-ai-agent
Warn
Audited by Socket on Mar 20, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is broadly consistent with a personal AI agent platform, but its actual footprint is very powerful: unsigned external app install, local command/file/browser/JS execution, autonomous scheduling, messaging bridges, and transitive GitHub skill installation. The main concern is not clear malware behavior, but disproportionate risk and trust expansion for a skill distributed by a different publisher than the software it asks users to install.
Confidence: 87%Severity: 84%
Audit Metadata