opencode-design-commands
Warn
Audited by Socket on Oct 7, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill’s purpose is coherent and the referenced OpenCode tooling appears official, but the embedded !`command` examples are actual pre-execution directives rather than inert documentation. That creates medium risk of unintended local command execution and some outbound GitHub queries at load/template time, though there is no clear credential theft, remote-code execution, or attacker exfiltration path.
Confidence: 89%Severity: 62%
Audit Metadata