skills/code-yeongyu/oh-my-opencode/review-work/Socket

review-work

Warn

Audited by Socket on Jul 19, 2026

1 alert found:

Security

SecuritySKILL.md

MEDIUM

SecurityMEDIUM

SKILL.md

SUSPICIOUS: the core review purpose is plausible, but the skill’s footprint is broad. Parallel autonomous agents, full-code prompt forwarding, and especially external context mining across GitHub/chat/docs create significant data-exposure and prompt-injection risk, while several required agent/tool dependencies are not provenance-verified in the skill text.

Confidence: 86%Severity: 76%

Audit Metadata

Analyzed At

Jul 19, 2026, 05:11 AM

Package URL

pkg:socket/skills-sh/code-yeongyu%2Foh-my-opencode%2Freview-work%2F@34ffb588361f3f3a636b5b38af7c14eec4a56ae1ccdd91aee372a7899c8a47bd