apimodels-image
Warn
Audited by Socket on Aug 18, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill is mostly coherent for an image-generation API wrapper, with scoped credential handling and no obvious malware patterns, but it sends user prompts and API credentials through apimodels.app as a third-party aggregation layer instead of official model-provider APIs, and it requires a non-public local script for execution. That makes the data flow and trust model moderately risky even though the behavior matches the stated purpose.
Confidence: 86%Severity: 58%
Audit Metadata