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.

A comprehensive red-teaming skill for assessing the security posture of Retrieval-Augmented Generation (RAG) pipelines. It systematically probes two critical injection surfaces: poisoned retrieved context (indirect prompt injection) and embedding manipulation. Use this skill to validate retrieval guardrails, ensure data leak prevention, and demonstrate vulnerabilities in LLM-powered knowledge assistants.

Workthreads analyzes a team's coding history across multiple repositories to generate a structured weekly status report. It clusters raw logs into 'work threads' and automatically tags their lifecycle status (new, open loops, closed, reverted). This is essential for leads needing a high-level, actionable summary of project progress, outstanding tasks, and completed features without reading thousands of lines of raw activity.