generate-image
Warn
Audited by Socket on May 14, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill is mostly aligned with its stated image-generation purpose, but it normalizes sending prompts and API keys to arbitrary 'OpenAI-compatible' endpoints instead of official APIs. That creates a meaningful credential-forwarding and data-flow trust risk, though there is no clear evidence of malware or deceptive hidden behavior in the supplied text.
Confidence: 82%Severity: 61%
Audit Metadata