skills/alexandru/skills/code-refine/Socket

code-refine

Warn

Audited by Socket on Oct 28, 2026

1 alert found:

Security

SecuritySKILL.md

MEDIUM

SecurityMEDIUM

SKILL.md

SUSPICIOUS: the core refinement purpose is coherent, but the skill expands its footprint by instructing the agent to install another skill from a personal GitHub repository. The main issue is transitive trust and mutable third-party skill content, not confirmed malicious behavior.

Confidence: 90%Severity: 74%

Audit Metadata

Analyzed At

Oct 28, 2026, 12:04 PM

Package URL

pkg:socket/skills-sh/alexandru%2Fskills%2Fcode-refine%2F@6aa0f8d03bc5e4f5e0328a53cdc95cf197254e9d