# Docs


- **Getting Started**
- [Quick Introduction](/docs/getting-started)
- [What Is LLM Red Teaming?](/docs/what-is-llm-red-teaming)

- **LLM Red Teaming**
- [Introduction to LLM Red Teaming](/docs/red-teaming-introduction)
- [YAML Configurations](/docs/red-teaming-yaml-cli)
- Concepts
  - [Test Case](/docs/red-teaming-test-case)
  - [Risk Assessment](/docs/red-teaming-risk-assessment)

- **Adversarial Attacks**
- [Attacks Introduction](/docs/red-teaming-adversarial-attacks)
- Single-Turn
  - [Adversarial Poetry](/docs/red-teaming-adversarial-attacks-adversarial-poetry)
  - [Authority Escalation](/docs/red-teaming-adversarial-attacks-authority-escalation)
  - [Base64](/docs/red-teaming-adversarial-attacks-base64-encoding)
  - [Character Stream](/docs/red-teaming-adversarial-attacks-character-stream)
  - [Context Flooding](/docs/red-teaming-adversarial-attacks-context-flooding)
  - [Embedded Instruction JSON](/docs/red-teaming-adversarial-attacks-embedded-instruction-json)
  - [Emotional Manipulation](/docs/red-teaming-adversarial-attacks-emotional-manipulation)
  - [Gray Box Attack](/docs/red-teaming-adversarial-attacks-gray-box-attack)
  - [Leetspeak](/docs/red-teaming-adversarial-attacks-leetspeak)
  - [Math Problem](/docs/red-teaming-adversarial-attacks-math-problem)
  - [Multilingual](/docs/red-teaming-adversarial-attacks-multilingual)
  - [Prompt Injection](/docs/red-teaming-adversarial-attacks-prompt-injection)
  - [Roleplay](/docs/red-teaming-adversarial-attacks-roleplay)
  - [ROT13](/docs/red-teaming-adversarial-attacks-rot13-encoding)
  - [Synthetic Context Injection](/docs/red-teaming-adversarial-attacks-synthetic-context-injection)
  - [Context Poisoning](/docs/red-teaming-agentic-attacks-context-poisoning)
  - [Input Bypass](/docs/red-teaming-agentic-attacks-input-bypass)
  - [Permission Escalation](/docs/red-teaming-agentic-attacks-permission-escalation)
  - [Semantic Manipulation](/docs/red-teaming-agentic-attacks-semantic-manipulation)
  - [System Override](/docs/red-teaming-agentic-attacks-system-override)
- Multi-Turn
  - [Bad Likert Judge](/docs/red-teaming-adversarial-attacks-bad-likert-judge)
  - [Crescendo Jailbreaking](/docs/red-teaming-adversarial-attacks-crescendo-jailbreaking)
  - [Linear Jailbreaking](/docs/red-teaming-adversarial-attacks-linear-jailbreaking)
  - [Sequential Jailbreaking](/docs/red-teaming-adversarial-attacks-sequential-jailbreaking)
  - [Tree Jailbreaking](/docs/red-teaming-adversarial-attacks-tree-jailbreaking)

- **Vulnerabilities**
- [Vulnerabilities Introduction](/docs/red-teaming-vulnerabilities)
- [Custom Vulnerability](/docs/red-teaming-custom-vulnerability)
- Data Privacy
  - [PII Leakage](/docs/red-teaming-vulnerabilities-pii-leakage)
  - [Prompt Leakage](/docs/red-teaming-vulnerabilities-prompt-leakage)
- Responsible AI
  - [Bias](/docs/red-teaming-vulnerabilities-bias)
  - [Child Protection](/docs/red-teaming-vulnerabilities-child-protection)
  - [Ethics](/docs/red-teaming-vulnerabilities-ethics)
  - [Fairness](/docs/red-teaming-vulnerabilities-fairness)
  - [Toxicity](/docs/red-teaming-vulnerabilities-toxicity)
- Security
  - [BFLA (Broken Function Level Authorization)](/docs/red-teaming-vulnerabilities-bfla)
  - [BOLA (Broken Object Level Authorization)](/docs/red-teaming-vulnerabilities-bola)
  - [RBAC (Role-Based Access Control)](/docs/red-teaming-vulnerabilities-rbac)
  - [Debug Access](/docs/red-teaming-vulnerabilities-debug-access)
  - [Shell Injection](/docs/red-teaming-vulnerabilities-shell-injection)
  - [SQL Injection](/docs/red-teaming-vulnerabilities-sql-injection)
  - [SSRF (Server-Side Request Forgery)](/docs/red-teaming-vulnerabilities-ssrf)
  - [Tool Metadata Poisoning](/docs/red-teaming-vulnerabilities-tool-metadata-poisoning)
  - [Cross-Context Retrieval](/docs/red-teaming-vulnerabilities-cross-context-retrieval)
  - [System Reconnaissance](/docs/red-teaming-vulnerabilities-system-reconnaissance)
- Safety
  - [Illegal Activity](/docs/red-teaming-vulnerabilities-illegal-activity)
  - [Graphic Content](/docs/red-teaming-vulnerabilities-graphic-content)
  - [Personal Safety](/docs/red-teaming-vulnerabilities-personal-safety)
  - [Unexpected Code Execution](/docs/red-teaming-vulnerabilities-unexpected-code-execution)
- Business
  - [Misinformation](/docs/red-teaming-vulnerabilities-misinformation)
  - [Intellectual Property](/docs/red-teaming-vulnerabilities-intellectual-property)
  - [Competition](/docs/red-teaming-vulnerabilities-competition)
- Agentic
  - [Goal Theft](/docs/red-teaming-agentic-vulnerabilities-goal-theft)
  - [Recursive Hijacking](/docs/red-teaming-agentic-vulnerabilities-recursive-hijacking)
  - [Excessive Agency](/docs/red-teaming-vulnerabilities-excessive-agency)
  - [Robustness](/docs/red-teaming-vulnerabilities-robustness)
  - [Indirect Instruction](/docs/red-teaming-vulnerabilities-indirect-instruction)
  - [Tool Orchestration Abuse](/docs/red-teaming-vulnerabilities-tool-orchestration-abuse)
  - [Agent Identity & Trust Abuse](/docs/red-teaming-vulnerabilities-agent-identity-abuse)
  - [Inter-Agent Communication Compromise](/docs/red-teaming-vulnerabilities-inter-agent-communication-compromise)
  - [Autonomous Agent Drift](/docs/red-teaming-vulnerabilities-autonomous-agent-drift)
  - [Exploit Tool Agent](/docs/red-teaming-vulnerabilities-exploit-tool-agent)
  - [External System Abuse](/docs/red-teaming-vulnerabilities-external-system-abuse)

- **Guidelines & Frameworks**
- [Introduction](/docs/frameworks-introduction)
- OWASP
  - [OWASP Top 10 for LLMs 2025](/docs/frameworks-owasp-top-10-for-llms)
  - [OWASP Top 10 for Agents 2026](/docs/frameworks-owasp-top-10-for-agentic-applications)
- [NIST AI RMF](/docs/frameworks-nist-ai-rmf)
- [MITRE ATLAS](/docs/frameworks-mitre-atlas)
- [EU AI Act](/docs/frameworks-eu-ai-act)
- [BeaverTails](/docs/frameworks-beavertails)
- [Aegis](/docs/frameworks-aegis)

- **Guardrails**
- [Introduction to LLM Guardrails](/docs/guardrails-introduction)
- Guards
  - [Prompt Injection Guard](/docs/guardrails-prompt-injection-guard)
  - [Topical Guard](/docs/guardrails-topical-guard)
  - [Toxicity Guard](/docs/guardrails-toxicity-guard)
  - [Privacy Guard](/docs/guardrails-privacy-guard)
  - [Illegal Guard](/docs/guardrails-illegal-guard)
  - [Hallucination Guard](/docs/guardrails-hallucination-guard)
  - [Cybersecurity Guard](/docs/guardrails-cybersecurity-guard)

- **Code Scanning**
- [Introduction to Code Scanning](/docs/code-scanning-introduction)
- [Code Scanning GitHub Bot](/docs/code-scanning-github-bot)

- **Others**
- [Data Privacy](/docs/data-privacy)