install-skills
Warn
Audited by Socket on Oct 9, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s behavior matches its stated purpose, but that purpose is itself high-trust: it installs other skills and executes an unpinned official CLI via npx, then restores mutable upstream skill content from GitHub default branches. No credential harvesting or mismatched data exfiltration is evident, but the transitive trust chain and unpinned remote execution make this a high security-risk skill despite coherent intent.
Confidence: 92%Severity: 74%
Audit Metadata