outreach
Warn
Audited by Socket on May 15, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: The skill's messaging purpose is coherent, but it relies on an unverified local `autark` CLI and supports autonomous outbound communication. No clear credential theft or exfiltration is present, yet the unresolved CLI trust and real-world action scope raise medium risk.
Confidence: 82%Severity: 56%
Audit Metadata