Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.
Scanned 9/10/2026
Install to Claude Code
Skills Directorynpx -y skills add nexuslinkproductions/yuri-os --skill cyber-continuous-llm-red-teaming-with-promptfoo --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Cyber Continuous Llm Red Teaming With Promptfoo?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/nexuslinkproductions-cyber-continuous-llm-red-teaming-with-promptfoo)More formats (shields.io, HTML) on the badges page.
---
name: cyber-continuous-llm-red-teaming-with-promptfoo
description: "Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress."
hide: true
---
<!-- GENERATED:YURI-CODEX-SKILL-ADAPTER:v1 -->
# YURI skill adapter
Authoritative source: `.claude/skills/cyber-continuous-llm-red-teaming-with-promptfoo/SKILL.md`
Authoritative source SHA-256: `eae5701e47ffd9ef344d46d4a564df85ba49def09e855f7a400ea46c3cc7808d`
Source class: `cyber-armed`
Before acting, read the authoritative source file above completely from beginning to end. If the governed source is absent, run `node _SYSTEM/Scripts/skill-recall.mjs --show cyber-continuous-llm-red-teaming-with-promptfoo` and read its complete verified output. Follow that source as the skill body; this adapter is a non-authoritative metadata-and-pointer projection.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling
