agentmail
Warn
Audited by Socket on Apr 16, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is coherent for an email API integration, but it grants AI agents autonomous messaging and account-verification capability with real-world impact. Data flows stay mostly within the claimed service, yet stale domain/SDK details reduce trust and the automation scope is higher risk than a typical utility skill.
Confidence: 84%Severity: 72%
Audit Metadata