RAXIT Core - Runtime AI eXecution Integrity & Trust
Core security scanning engine for AI agent applications built with Rust. Provides high-performance static analysis, security vulnerability detection, and compliance validation for AI agent codebases.
Features
- Fast AST Parsing: Uses tree-sitter for high-performance Python code analysis
- Framework Detection: Automatically detects PydanticAI, LangGraph, CrewAI, AutoGen, Swarm
- Security Analysis: 4 built-in analyzers for comprehensive security coverage
- Incremental Scanning: File-level caching for fast re-scans
- Multi-format Output: JSON and YAML serialization support
Security Analyzers
- Trust Boundary Analyzer - Meta's "Rule of Two" for unsafe component detection
- Secret Detection - Find exposed API keys, credentials, and sensitive data
- Memory Detection - Track vector stores, databases, and persistence layers
- Network Detection - Identify HTTP calls, API clients, and external communications
- Data Provenance - CaMeL-style taint analysis for data flow tracking
Quick Start
use ;
// Scan a directory for AI agent code
let config = default
.with_path
.with_format;
let result = scan?;
// Access discovered assets
println!;
println!;
println!;
// Serialize to YAML
println!;
# Ok::
Advanced Usage
use ;
// Create a custom configuration
let config = new
.with_format;
// Run scan
let result = scan?;
// Access specific findings
for finding in &result.secret_findings
// Check for critical issues
let critical_secrets = result.secret_findings
.iter
.filter
.count;
let critical_flows = result.provenance_findings
.iter
.filter
.count;
println!;
# Ok::