Skill UI

Automate security regression testing for Large Language Model (LLM) applications by integrating Promptfoo and DeepTeam into CI/CD pipelines. This skill enforces a critical security gate, automatically testing endpoints against OWASP LLM Top 10, OWASP Agentic threats, and common jailbreaks/prompt injections. It ensures that security patches do not regress over time due to prompt or model changes, providing continuous risk monitoring.

Utilize this skill to assess the health, adoption, and performance metrics of published EAS Updates directly via the CLI. It reports critical data points including crash rates, unique user counts, install volumes, payload size, and the split between embedded and OTA users, making it essential for post-publish monitoring and regression detection.