OverviewHistoryStatsSecurity
Security
Independent checks from skills.sh's audit partners.
Independent checks from skills.sh's audit partners.
Independent checks from skills.sh's audit partners.
Fail3 providerslatest audit Aug 25, 2026
Independent checks from skills.sh's audit partners.
This skill provides a pipeline for generating image referring-expression annotations using Vision-Language Models (VLMs). It uses standard tools like Docker, NVIDIA TAO Toolkit, and vLLM. No malicious patterns or security risks were detected.
Detected behaviors
No alerts
2 issues