gpt-image
Warn
Audited by Socket on Jul 10, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the core image-generation purpose is coherent, but the skill is heavier than necessary because it requires broad Bash access, a separate CLI, and transitive installation of another skill. Data appears to route through inference.sh as intended, not an obvious exfiltration endpoint, so this is not confirmed malware; the main concern is supply-chain and transitive trust rather than malicious intent.
Confidence: 84%Severity: 64%
Audit Metadata