companionship
Warn
Audited by Socket on May 14, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: The skill is internally consistent with its stated companionship purpose and its data flows stay on the claimed inbed.ai service, so it does not look like credential theft or malware. However, it gives an AI agent the ability to autonomously perform external social actions—messaging, swiping, and relationship changes—which is disproportionate and high-impact enough to classify as suspicious rather than benign.
Confidence: 84%Severity: 67%
Audit Metadata