Initial scaffold: GyanDoot v2.0 in Rust

Full Cargo workspace with 11 crates:
- gyandoot-core: Shared types, config, error types
- gyandoot-agent: Agent loop, tool execution, context compression
- gyandoot-providers: LLM provider abstraction (OpenAI, Anthropic, Ollama)
- gyandoot-memory: MemPalace persistent memory system
- gyandoot-platform: Platform adapters (Telegram, Discord, Webhook, CLI)
- gyandoot-security: Credential vault, sanitizer, threat detector
- gyandoot-kanban: Task decomposition, swarm orchestration, diagnostics
- gyandoot-subagents: Sub-agent spawning and orchestration
- gyandoot-skills: Skills discovery, loading, preprocessing, bundles
- gyandoot-profile: Multi-agent profile manager
- gyandoot-gateway: Gateway sessions, routing, access control

Plus: CLI entry point with clap, cross-platform installer script,
KANBAN.md, .gnpl/AGENTS.md

Workspace compiles clean: cargo check passes with 0 errors.
This commit is contained in:
2026-06-11 20:04:12 +05:30
commit 851c838ca5
53 changed files with 8037 additions and 0 deletions

View File

@@ -0,0 +1,112 @@
//! Input sanitizer — prevents injection and dangerous patterns.
use tracing::debug;
/// Sanitizes user input before it reaches the agent or LLM.
///
/// Blocks or escapes shell metacharacters, path traversal attempts,
/// and other potentially dangerous input patterns.
pub struct Sanitizer {
blocked_patterns: Vec<String>,
max_length: usize,
}
impl Sanitizer {
/// Create a new sanitizer with defaults.
pub fn new() -> Self {
Self {
blocked_patterns: vec![
"`rm -rf /".to_string(),
"`rm -rf ~".to_string(),
"`sudo ".to_string(),
"| sh".to_string(),
"| bash".to_string(),
"| powershell".to_string(),
"`curl ".to_string(),
"`wget ".to_string(),
],
max_length: 100_000,
}
}
/// Sanitize a string input.
///
/// Returns the cleaned string. Currently performs length limiting
/// and basic pattern blocking. Extensible for more sophisticated
/// sanitization in the future.
pub fn sanitize(&self, input: &str) -> String {
// Truncate excessively long input
let mut cleaned = if input.len() > self.max_length {
let truncated: String = input.chars().take(self.max_length).collect();
debug!("Input truncated from {} to {} chars", input.len(), self.max_length);
truncated
} else {
input.to_string()
};
// Block known dangerous patterns (case-insensitive)
for pattern in &self.blocked_patterns {
if cleaned.to_lowercase().contains(&pattern.to_lowercase()) {
debug!("Blocked dangerous pattern: {}", pattern);
cleaned = cleaned.replace(pattern, "[blocked]");
}
}
cleaned
}
/// Check if input contains any blocked patterns.
pub fn is_dangerous(&self, input: &str) -> bool {
let lower = input.to_lowercase();
self.blocked_patterns
.iter()
.any(|p| lower.contains(&p.to_lowercase()))
}
/// Register an additional blocked pattern.
pub fn block_pattern(&mut self, pattern: String) {
self.blocked_patterns.push(pattern);
}
}
impl Default for Sanitizer {
fn default() -> Self {
Self::new()
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn test_sanitize_dangerous_pattern() {
let sanitizer = Sanitizer::new();
let result = sanitizer.sanitize("run `rm -rf /` please");
assert!(!result.contains("rm -rf /"));
}
#[test]
fn test_sanitize_safe_input() {
let sanitizer = Sanitizer::new();
let result = sanitizer.sanitize("Hello, how are you?");
assert_eq!(result, "Hello, how are you?");
}
#[test]
fn test_is_dangerous() {
let sanitizer = Sanitizer::new();
assert!(sanitizer.is_dangerous("run | bash now"));
assert!(!sanitizer.is_dangerous("run a Python script"));
}
#[test]
fn test_truncate_long_input() {
let sanitizer = Sanitizer {
max_length: 10,
..Sanitizer::new()
};
let result = sanitizer.sanitize("hello world this is long");
assert_eq!(result.len(), 10);
}
}