feature-plan
Warn
Audited by Socket on Mar 29, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
BENIGN overall in purpose and data flow: the capabilities fit a local feature-planning workflow, and no credential harvesting or outbound exfiltration is evident. The main concern is install/execution trust from opaque local scripts in ~/.claude/scripts, which raises security risk despite otherwise coherent behavior.
Confidence: 87%Severity: 72%
Audit Metadata