Files
prowler/docs/developer-guide/llm-details.mdx
2025-10-15 16:38:56 +02:00

105 lines
5.5 KiB
Plaintext

---
title: 'LLM Provider'
---
This page details the [Large Language Model (LLM)](https://en.wikipedia.org/wiki/Large_language_model) provider implementation in Prowler.
The LLM provider enables security testing of language models using red team techniques. By default, Prowler uses the built-in LLM configuration that targets OpenAI models with comprehensive security test suites. To configure it, follow the [LLM getting started guide](/user-guide/providers/llm/getting-started-llm).
## LLM Provider Classes Architecture
The LLM provider implementation follows the general [Provider structure](/developer-guide/provider). This section focuses on the LLM-specific implementation, highlighting how the generic provider concepts are realized for LLM security testing in Prowler. For a full overview of the provider pattern, base classes, and extension guidelines, see [Provider documentation](/developer-guide/provider).
### Main Class
- **Location:** [`prowler/providers/llm/llm_provider.py`](https://github.com/prowler-cloud/prowler/blob/master/prowler/providers/llm/llm_provider.py)
- **Base Class:** Inherits from `Provider` (see [base class details](https://github.com/prowler-cloud/prowler/blob/master/prowler/providers/common/provider.py)).
- **Purpose:** Central orchestrator for LLM-specific logic, configuration management, and integration with promptfoo for red team testing.
- **Key LLM Responsibilities:**
- Initializes and manages LLM configuration using promptfoo.
- Validates configuration and sets up the LLM testing context.
- Loads and manages red team test configuration, plugins, and target models.
- Provides properties and methods for downstream LLM security testing.
- Integrates with promptfoo for comprehensive LLM security evaluation.
### Data Models
- **Location:** [`prowler/providers/llm/models.py`](https://github.com/prowler-cloud/prowler/blob/master/prowler/providers/llm/models.py)
- **Purpose:** Define structured data for LLM output options and configuration.
- **Key LLM Models:**
- `LLMOutputOptions`: Customizes output filename logic for LLM-specific reporting.
### LLM Security Testing Integration
- **Location:** [`prowler/providers/llm/llm_provider.py`](https://github.com/prowler-cloud/prowler/blob/master/prowler/providers/llm/llm_provider.py)
- **Purpose:** Integrates with promptfoo for comprehensive LLM security testing.
- **Key LLM Responsibilities:**
- Executes promptfoo red team evaluations against target LLMs.
- Processes security test results and converts them to Prowler reports.
- Manages test concurrency and progress tracking.
- Handles real-time streaming of test results.
### Configuration Management
The LLM provider uses promptfoo configuration files to define:
- **Target Models**: The LLM models to test (e.g., OpenAI GPT, Anthropic Claude)
- **Red Team Plugins**: Security test suites (OWASP, MITRE, NIST, EU AI Act)
- **Test Parameters**: Concurrency, test counts, and evaluation criteria
### Default Configuration
Prowler includes a comprehensive default LLM configuration that:
- Targets OpenAI models by default
- Includes multiple security test frameworks (OWASP, MITRE, NIST, EU AI Act)
- Provides extensive test coverage for LLM security vulnerabilities
- Supports custom configuration for specific testing needs
## Specific Patterns in LLM Security Testing
The LLM provider implements security testing through integration with promptfoo, following these patterns:
### Red Team Testing Framework
- **Plugin-based Architecture**: Uses promptfoo plugins for different security test categories
- **Comprehensive Coverage**: Includes OWASP LLM Top 10, MITRE ATLAS, NIST AI Risk Management, and EU AI Act compliance
- **Real-Time Evaluation**: Streams test results as they are generated
- **Progress Tracking**: Provides detailed progress information during test execution
### Test Execution Flow
1. **Configuration Loading**: Loads promptfoo configuration with target models and test plugins
2. **Test Generation**: Generates security test cases based on configured plugins
3. **Concurrent Execution**: Runs tests with configurable concurrency limits
4. **Result Processing**: Converts promptfoo results to Prowler security reports
5. **Progress Monitoring**: Tracks and displays test execution progress
### Security Test Categories
The LLM provider supports comprehensive security testing across multiple frameworks:
- **OWASP LLM Top 10**: Covers prompt injection, data leakage, and model security
- **MITRE ATLAS**: Adversarial threat landscape for AI systems
- **NIST AI Risk Management**: AI system risk assessment and mitigation
- **EU AI Act**: European Union AI regulation compliance
- **Custom Tests**: Support for organization-specific security requirements
## Error Handling and Validation
The LLM provider includes comprehensive error handling for:
- **Configuration Validation**: Ensures valid promptfoo configuration files
- **Model Access**: Handles authentication and access issues with target LLMs
- **Test Execution**: Manages test failures and timeout scenarios
- **Result Processing**: Handles malformed or incomplete test results
## Integration with Prowler Ecosystem
The LLM provider seamlessly integrates with Prowler's existing infrastructure:
- **Output Formats**: Supports all Prowler output formats (JSON, CSV, HTML, etc.)
- **Compliance Frameworks**: Integrates with Prowler's compliance reporting
- **Fixer Integration**: Supports automated remediation recommendations
- **Dashboard Integration**: Compatible with Prowler App for centralized management