Add WASM sandbox secure API extension

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
+7
View File
@@ -67,6 +67,13 @@ pgvector = { version = "0.4", features = ["postgres"] }
# WASM sandbox for untrusted tool execution
wasmtime = { version = "28", features = ["component-model"] }
# Cryptography for secrets management
aes-gcm = "0.10"
hkdf = "0.12"
sha2 = "0.10"
blake3 = "1"
rand = "0.8"
[dev-dependencies]
tokio-test = "0.4"
testcontainers-modules = { version = "0.11", features = ["postgres"] }