create
Warn
Audited by Socket on Oct 22, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s core purpose is legitimate and mostly aligned, but it expands into high-impact autonomous actions (commit, push, release), installs trust transitively in other skills/agents, and forwards a locally stored GitHub token into release commands. This looks like a developer workflow skill, not malware, but its privileges and credential handling are riskier than a simple plugin scaffolder.
Confidence: 90%Severity: 72%
Audit Metadata