Documentation index¶
This is an Atlas mirror of the upstream project documentation.
Code Scanning¶
Configuration¶
- Caching
- Chat
- Datasets
- Classifier
- Deterministic
- Guardrails
- Index
- Javascript
- Agent Rubric
- Answer Relevance
- Context Faithfulness
- Context Recall
- Context Relevance
- Conversation Relevance
- Factuality
- G Eval
- Index
- Llm Rubric
- Max Score
- Model Graded Closedqa
- Pi
- Search Rubric
- Select Best
- Moderation
- Python
- Ruby
- Similar
- Guide
- Huggingface Datasets
- Modular Configs
- Outputs
- Parameters
- Prompts
- Rate Limits
- Reference
- Scenarios
- Telemetry
- Test Cases
- Tools
Enterprise¶
- Audit Logging
- Authentication
- Findings
- Guardrails
- Index
- Red Teams
- Remediation Reports
- Service Accounts
- Sso
- Teams
- Webhooks
Guides¶
- Azure Vs Openai
- Chatbase Redteam
- Choosing Best Gpt Model
- Compare Open Source Models
- Deepseek Benchmark
- Evaling With Harmbench
- Evaluate Coding Agents
- Evaluate Crewai
- Evaluate Elevenlabs
- Evaluate Google Adk
- Evaluate Json
- Evaluate Langgraph
- Evaluate Llm Temperature
- Evaluate Openai Agents Python
- Evaluate Openai Assistants
- Evaluate Osworld With Inspect
- Evaluate Rag
- Factuality Eval
- Google Cloud Model Armor
- Gpt 5.2 Vs O3
- Gpt Mmlu Comparison
- Gpt Vs Claude Vs Gemini
- Hle Benchmark
- Index
- Langchain Prompttemplate
- Llama2 Uncensored Benchmark Ollama
- Llm As A Judge
- Llm Redteaming
- Mixtral Vs Gpt
- Multimodal Red Team
- Prevent Llm Hallucinations
- Qwen Benchmark
- Sandboxed Code Evals
- Test Agent Skills
- Testing Guardrails
- Testing Llm Chains
- Text To Sql Evaluation
Integrations¶
- Agent Skill
- Aws Codecommit
- Azure Pipelines
- Bitbucket Pipelines
- Burp
- Ci Cd
- Circle Ci
- Github Action
- Gitlab Ci
- Google Sheets
- Helicone
- Jenkins
- Jest
- Langfuse
- Looper
- Mcp Server
- Mcp
- Mocha Chai
- N8N
- Portkey
- Python
- Sharepoint
- Sonarqube
- Splunk
- Travis Ci
Model Audit¶
Providers¶
- A2A
- Abliteration
- Ai21
- Aimlapi
- Alibaba
- Anthropic
- Atlascloud
- Aws Bedrock
- Azure
- Bedrock Agents
- Browser
- Cerebras
- Claude Agent Sdk
- Cloudera
- Cloudflare Ai
- Cloudflare Gateway
- Cohere
- Cometapi
- Custom Api
- Custom Script
- Databricks
- Deepseek
- Docker
- Echo
- Elevenlabs
- Envoy
- F5
- Fal
- Fireworks
- Flexai
- Github
- Go
- Groq
- Helicone
- Http
- Huggingface
- Hyperbolic
- Ibm Bam
- Index
- Jfrog
- Litellm
- Llama.Cpp
- Llamaapi
- Llamafile
- Localai
- Manual Input
- Mcp
- Meta
- Minimax
- Mistral
- Mlflow Gateway
- Modelslab
- Moonshot
- N8N
- Novita
- Nscale
- Nvidia
- Ollama
- Openai Agents Api
- Openai Agents
- Openai Chatkit
- Openai Codex App Server
- Openai Codex Sdk
- Openai Codex Security
- Openai Decisions
- Openai Live
- Openai
- Openclaw
- Opencode Sdk
- Openinterpreter
- Openllm
- Openrouter
- Orcarouter
- Perplexity
- Python
- Quiverai
- Replicate
- Ruby
- Sagemaker
- Sequence
- Simulated User
- Slack
- Snowflake
- Text Generation Webui
- Togetherai
- Transformers
- Truefoundry
- Typesafe
- Vercel
- Vertex
- Vllm
- Voyage
- Watsonx
- Webhook
- Websocket
- Xai
Red Team¶
- Agents
- Architecture
- Coding Agents
- Configuration
- Discovery
- Dod Ai Ethics
- Eu Ai Act
- Foundation Models
- Gdpr
- Index
- Index
- Iso 42001
- Llm Agents
- Llm Supply Chain
- Llm Vulnerability Types
- Mcp Security Testing
- Mitre Atlas
- Model Drift
- Multi Input
- Nist Ai Rmf
- Owasp Agentic Ai
- Owasp Api Top 10
- Owasp Llm Top 10
- Aegis
- Age Bias
- Ascii Smuggling
- Beavertails
- Bfla
- Bias
- Bola
- Coding Agent
- Competitors
- Context Compliance Attack
- Contracts
- Coppa
- Cross Session Leak
- Custom
- Cyberseceval
- Data Exfil
- Debug Access
- Disability Bias
- Divergent Repetition
- Donotanswer
- Ecommerce
- Excessive Agency
- Ferpa
- Financial
- Gender Bias
- Goal Misalignment
- Hallucination
- Harmbench
- Harmful
- Hijacking
- Imitation
- Index
- Indirect Prompt Injection
- Insurance
- Intent
- Malicious Code
- Mcp
- Medical
- Memory Poisoning
- Model Identification
- Off Topic
- Overreliance
- Pharmacy
- Pii
- Pliny
- Policy
- Politics
- Prompt Extraction
- Race Bias
- Rag Document Exfiltration
- Rag Poisoning
- Rag Source Attribution
- Rbac
- Realestate
- Reasoning Dos
- Religion
- Shell Injection
- Special Token Injection
- Sql Injection
- Ssrf
- System Prompt Override
- Teen Safety
- Telecom
- Tool Discovery
- Toxic Chat
- Unsafebench
- Unverifiable Claims
- Vlguard
- Vlsu
- Wordplay
- Xstest
- Quickstart
- Rag
- Risk Scoring
- Arabic Presentation Forms
- Audio
- Authoritative Markup Injection
- Base64
- Basic
- Best Of N
- Citation
- Composite Jailbreaks
- Custom Strategy
- Custom
- Gcg
- Goat
- Goblin
- Hex
- Homoglyph
- Hydra
- Image
- Index
- Indirect Web Pwn
- Iterative
- Jailbreak Templates
- Layer
- Leetspeak
- Likert
- Math Prompt
- Meta
- Mischievous User
- Multi Turn
- Other Encodings
- Prompt Injection
- Retry
- Rot13
- Tree
- Video
- Attack Generation
- Best Practices
- Connecting To Targets
- Data Handling
- False Positives
- Grading Results
- Inference Limit
- Linking Targets
- Multi Turn Sessions
- Multiple Response Types
- Overview
- Remote Generation