inbox-zero
Warn
Audited by Socket on Jul 28, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the stated purpose matches inbox triage, but the skill grants broad cross-system access and permits autonomous state-changing actions on untrusted inbound content. The biggest risks are prompt-injection-driven misclassification/actions and unclear trust boundaries around the referenced Swan/internal agent tooling, not confirmed malware.
Confidence: 87%Severity: 79%
Audit Metadata