gitops/optimclaw
1
0
Fork 0
mirror of https://github.com/outbackdingo/optimclaw.git synced 2026-08-30 16:19:21 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add WASM sandbox secure API extension

Browse Source 
Extends the WASM sandbox with HTTP API capabilities, secrets management,
tool aliasing, and leak detection. Key security principle: WASM never
sees credentials, injection happens at host boundary.

New modules:
- secrets: AES-256-GCM encrypted storage with HKDF key derivation
- leak_detector: Aho-Corasick + regex pattern matching for secret exfiltration
- capabilities: Extended capability system (HTTP, ToolInvoke, Secrets)
- allowlist: HTTP endpoint validation with glob patterns
- credential_injector: Host-boundary credential injection
- rate_limiter: Sliding window per-tool rate limiting
- storage: WASM binary storage with BLAKE3 integrity verification

Leak detection happens at two points:
1. Before HTTP request (prevents exfiltration via URL/headers/body)
2. After response (prevents exposure in outputs returned to WASM)

Co-Authored-By: Claude Opus 4.5 <[email protected]>
This commit is contained in:
Illia Polosukhin
2026-02-02 23:22:52 -08:00
co-authored by Claude Opus 4.5
parent 45bbfa026d
commit 32bfd24154
21 changed files with 5115 additions and 66 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/safety/mod.rs
+6
View File
@@ -5,11 +5,17 @@
//! - Sanitizing tool outputs before they reach the LLM
//! - Validating inputs before processing
//! - Enforcing safety policies
//! - Detecting secret leakage in outputs
mod leak_detector;
mod policy;
mod sanitizer;
mod validator;
pub use leak_detector::{
LeakAction, LeakDetectionError, LeakDetector, LeakMatch, LeakPattern, LeakScanResult,
LeakSeverity,
};
pub use policy::{Policy, PolicyRule, Severity};
pub use sanitizer::{InjectionWarning, SanitizedOutput, Sanitizer};
pub use validator::{ValidationResult, Validator};