oh-my-opencode

SUSPICIOUS. The skill’s capabilities broadly match its stated purpose as a multi-agent OpenCode orchestrator, but its footprint is high-risk: unpinned package execution, autonomous continuation loops, and external-content research combined with agent action capabilities. There is no clear evidence of credential harvesting or malicious exfiltration, so this is not confirmed malware, but it is a medium/high-risk orchestration skill that should be used only with strong user oversight.