ai-gpt-image-2
Warn
Audited by Socket on Jun 13, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill’s behavior is broadly consistent with a hosted image-diagnosis assistant, but it routes user materials and an API key to an external service with limited independent verification and without the runner code present for review. No clear malware or deceptive capability is evident, but the remote processing and credential forwarding create medium security risk.
Confidence: 100%Severity: 60%
Audit Metadata