Security audit
Claude Code Enhancement
Security checks across malware telemetry and agentic risk
Overview
The skill’s multi-agent and memory features match its purpose, but its permission and isolation safeguards are weaker than the safety claims suggest.
Review this skill carefully before installing. Keep permission mode on ask/default, avoid bypass mode, use a git worktree or backups before allowing workers to edit files or run commands, verify the source if manually installing, and regularly inspect or clear the persistent memory files.
VirusTotal
49/49 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.