afterself
Warn
Audited by Socket on Mar 21, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is coherent as a digital-legacy agent, but its actual footprint is high risk: it can autonomously perform irreversible real-world actions, route data to arbitrary webhooks, unlock encrypted plans with a vault password, and execute mandatory crypto transfers. The npm installs themselves look ordinary, but the operational scope and external action pathways are disproportionate and dangerous for an AI agent.
Confidence: 92%Severity: 89%
Audit Metadata