admin/openhuman
1
0
Fork 0
mirror of https://github.com/tinyhumansai/openhuman.git synced 2026-07-30 06:32:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(security): enforce prompt-injection guard before model and tool execution (#1175)

Browse Source
This commit is contained in:
YellowSnnowmann
2026-05-04 02:30:22 -07:00
committed by GitHub
parent 05ce526e85
commit 995e5ccccb
18 changed files with 1237 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/ARCHITECTURE.md
+1
View File
@@ -279,6 +279,7 @@ Skill sync now also feeds a bounded **user working memory** layer (preferences,
- **Auth handoff**: Web-to-desktop authentication uses single-use login tokens with 5-minute TTL, exchanged via Rust HTTP client (bypasses CORS)
- **Network TLS**: All WebSocket and HTTP connections use rustls — no dependency on platform OpenSSL
- **State management**: Sensitive data lives in Redux (memory) and OS keychain (persistent). No localStorage for credentials or tokens
- **Prompt injection guard**: User prompts are normalized/scored and enforced server-side (`allow | review | block`) before model/tool execution. See [`docs/PROMPT_INJECTION_GUARD.md`](./PROMPT_INJECTION_GUARD.md)
---