{"id":"252c7bb9-f4e1-4bfa-a0b6-8e74d78ca900","shortId":"gGrjxv","kind":"skill","title":"Red-team agent workflows for jailbreaks, prompt injection, and policy failures with DeepTeam","tagline":"Run local adversarial attack passes against agents, RAG pipelines, and chatbots to surface concrete failure classes before production rollout.","description":"# Red-team agent workflows for jailbreaks, prompt injection, and policy failures with DeepTeam\n\nRun local adversarial attack passes against agents, RAG pipelines, and chatbots to surface concrete failure classes before production rollout.\n\n## Prerequisites\n\nPython environment, local or configured LLM access for chosen attacks\n\n## Installation\n\nUse the upstream install or setup path that matches your environment:\n- pip install -U deepteam\n\nRequirements and caveats from upstream:\n- 🔗 Run red teaming from the **CLI** with YAML configs, or programmatically in Python.\n- DeepTeam does not require you to define what LLM system you are red teaming — because neither will malicious users. All you need to do is install deepteam, define a model_callback, and you're good to go.\n- python\n\nBasic usage or getting-started notes:\n- <a href=\"#-quickstart\">Getting Started</a> |\n- 📐 50+ ready-to-use [vulnerabilities](https://www.trydeepteam.com/docs/red-teaming-vulnerabilities) (all with explanations) powered by **ANY** LLM of your choice. Each vulnerability uses LLM-as-a-Judge metrics that run...\n- ## Red Team Your First LLM\n\n- Source: https://github.com/confident-ai/deepteam\n- Extracted from upstream docs: https://raw.githubusercontent.com/confident-ai/deepteam/HEAD/README.md\n\n## Documentation\n\n- https://github.com/confident-ai/deepteam\n\n## Source\n\n- [Agent Skill Exchange](https://agentskillexchange.com/skills/red-team-agent-workflows-for-jailbreaks-prompt-injection-and-policy-failures-with-deepteam/)","tags":["red","team","agent","workflows","for","jailbreaks","prompt","injection","and","policy","failures","with"],"capabilities":["skill","source-agentskillexchange","skill-red-team-agent-workflows-for-jailbreaks-prompt-injection-and-policy-failures-with-deepteam","topic-agent-skills","topic-ai-agents","topic-ai-tools","topic-awesome-list","topic-claude-code","topic-codex","topic-cursor","topic-llm","topic-mcp","topic-npx-skills","topic-openclaw","topic-skills-catalog"],"categories":["skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/agentskillexchange/skills/red-team-agent-workflows-for-jailbreaks-prompt-injection-and-policy-failures-with-deepteam","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add agentskillexchange/skills","source_repo":"https://github.com/agentskillexchange/skills","install_from":"skills.sh"}},"qualityScore":"0.454","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 8 github stars · SKILL.md body (1,509 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T19:12:02.564Z","embedding":null,"createdAt":"2026-05-18T13:18:47.133Z","updatedAt":"2026-05-18T19:12:02.564Z","lastSeenAt":"2026-05-18T19:12:02.564Z","tsv":"'/confident-ai/deepteam':197,208 '/confident-ai/deepteam/head/readme.md':204 '/docs/red-teaming-vulnerabilities)':167 '/skills/red-team-agent-workflows-for-jailbreaks-prompt-injection-and-policy-failures-with-deepteam/)':215 '50':159 'access':74 'adversari':17,50 'agent':4,21,37,54,210 'agentskillexchange.com':214 'agentskillexchange.com/skills/red-team-agent-workflows-for-jailbreaks-prompt-injection-and-policy-failures-with-deepteam/)':213 'attack':18,51,77 'basic':150 'callback':142 'caveat':96 'chatbot':25,58 'choic':177 'chosen':76 'class':30,63 'cli':104 'concret':28,61 'config':107 'configur':72 'deepteam':14,47,93,112,138 'defin':118,139 'doc':201 'document':205 'environ':69,89 'exchang':212 'explan':170 'extract':198 'failur':12,29,45,62 'first':192 'get':154,157 'getting-start':153 'github.com':196,207 'github.com/confident-ai/deepteam':195,206 'go':148 'good':146 'inject':9,42 'instal':78,82,91,137 'jailbreak':7,40 'judg':185 'llm':73,120,174,182,193 'llm-as-a-judg':181 'local':16,49,70 'malici':129 'match':87 'metric':186 'model':141 'need':133 'neither':127 'note':156 'pass':19,52 'path':85 'pip':90 'pipelin':23,56 'polici':11,44 'power':171 'prerequisit':67 'product':32,65 'programmat':109 'prompt':8,41 'python':68,111,149 'rag':22,55 'raw.githubusercontent.com':203 'raw.githubusercontent.com/confident-ai/deepteam/head/readme.md':202 're':145 'readi':161 'ready-to-us':160 'red':2,35,100,124,189 'red-team':1,34 'requir':94,115 'rollout':33,66 'run':15,48,99,188 'setup':84 'skill':211 'skill-red-team-agent-workflows-for-jailbreaks-prompt-injection-and-policy-failures-with-deepteam' 'sourc':194,209 'source-agentskillexchange' 'start':155,158 'surfac':27,60 'system':121 'team':3,36,101,125,190 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-tools' 'topic-awesome-list' 'topic-claude-code' 'topic-codex' 'topic-cursor' 'topic-llm' 'topic-mcp' 'topic-npx-skills' 'topic-openclaw' 'topic-skills-catalog' 'u':92 'upstream':81,98,200 'usag':151 'use':79,163,180 'user':130 'vulner':164,179 'workflow':5,38 'www.trydeepteam.com':166 'www.trydeepteam.com/docs/red-teaming-vulnerabilities)':165 'yaml':106","prices":[{"id":"7a6e0345-d9ae-4f99-9f31-99fa65b59134","listingId":"252c7bb9-f4e1-4bfa-a0b6-8e74d78ca900","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"agentskillexchange","category":"skills","install_from":"skills.sh"},"createdAt":"2026-05-18T13:18:47.133Z"}],"sources":[{"listingId":"252c7bb9-f4e1-4bfa-a0b6-8e74d78ca900","source":"github","sourceId":"agentskillexchange/skills/red-team-agent-workflows-for-jailbreaks-prompt-injection-and-policy-failures-with-deepteam","sourceUrl":"https://github.com/agentskillexchange/skills/tree/main/skills/red-team-agent-workflows-for-jailbreaks-prompt-injection-and-policy-failures-with-deepteam","isPrimary":false,"firstSeenAt":"2026-05-18T13:18:47.133Z","lastSeenAt":"2026-05-18T19:12:02.564Z"}],"details":{"listingId":"252c7bb9-f4e1-4bfa-a0b6-8e74d78ca900","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"agentskillexchange","slug":"red-team-agent-workflows-for-jailbreaks-prompt-injection-and-policy-failures-with-deepteam","github":{"repo":"agentskillexchange/skills","stars":8,"topics":["agent-skills","ai-agents","ai-tools","awesome-list","claude-code","codex","cursor","llm","mcp","npx-skills","openclaw","skills-catalog"],"license":"mit","html_url":"https://github.com/agentskillexchange/skills","pushed_at":"2026-05-18T19:02:17Z","description":"The open catalog of AI agent skills — 2,000+ security-scanned skills for Claude Code, Cursor, Codex, and more.","skill_md_sha":"cd2673bc0c42fc5667af31f8983b2ecaccc250db","skill_md_path":"skills/red-team-agent-workflows-for-jailbreaks-prompt-injection-and-policy-failures-with-deepteam/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/agentskillexchange/skills/tree/main/skills/red-team-agent-workflows-for-jailbreaks-prompt-injection-and-policy-failures-with-deepteam"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"Red-team agent workflows for jailbreaks, prompt injection, and policy failures with DeepTeam","description":"Run local adversarial attack passes against agents, RAG pipelines, and chatbots to surface concrete failure classes before production rollout."},"skills_sh_url":"https://skills.sh/agentskillexchange/skills/red-team-agent-workflows-for-jailbreaks-prompt-injection-and-policy-failures-with-deepteam"},"updatedAt":"2026-05-18T19:12:02.564Z"}}