OverviewHistoryStatsSecurity
Security
Independent checks from skills.sh's audit partners.
Independent checks from skills.sh's audit partners.
Independent checks from skills.sh's audit partners.
Warn4 providerslatest audit Mar 18, 2026
Independent checks from skills.sh's audit partners.
This skill implements a self-modifying agent architecture that automatically updates other skill files and installs shell-based hooks. While these are core features for its intended purpose of 'self-improvement,' they introduce significant security risks including persistence via configuration modification and susceptibility to instruction poisoning from interaction data.
Detected behaviors
1 alert: gptAnomaly
No issues
2/10 files flagged