gpt-image-2-gen
Warn
Audited by Socket on May 12, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill is broadly consistent with its stated image-generation purpose, but it routes prompts and API credentials through EvoLink rather than OpenAI directly and supports optional callback delivery to arbitrary URLs. With no script contents or external trust verification provided, this is best classified as medium-risk third-party credential/data forwarding rather than confirmed malware.
Confidence: 100%Severity: 60%
Audit Metadata