Skill Detail
Red-team agent workflows for jailbreaks, prompt injection, and policy failures with DeepTeam
Run local adversarial attack passes against agents, RAG pipelines, and chatbots to surface concrete failure classes before production rollout.
Security & VerificationMulti-Framework
Security & Verification
Multi-Framework
Security Reviewed
⭐ 1.6k GitHub stars
INSTALL WITH ANY AGENT
npx skills add agentskillexchange/skills --skill red-team-agent-workflows-for-jailbreaks-prompt-injection-and-policy-failures-with-deepteam
Works best when you want a reusable capability, not another fragile one-off prompt.
At a glance
Tools required
Python environment, local or configured LLM access for chosen attacks
Install & setup
Follow the repository quickstart to install DeepTeam, configure the model or local runtime you want to use for attack generation and judging, then run red-team passes against the target agent or LLM system and review the reported failures.
Author
Confident AI
Publisher
Organization
Last updated
Apr 22, 2026
Quick brief
Use DeepTeam when you want to simulate attacks against an agent workflow before trusting it in production. The upstream workflow is clear: choose built-in vulnerability classes, run local red-team tests against an agent, RAG system, or chatbot, inspect binary pass/fail results with reasoning, and use those findings to harden prompts, tools, and policies. The scope boundary is adversarial red-team execution and review for LLM systems, not a generic security platform or plain model-evaluation listing.