From 13a19c5d12d943b121c6006481de4800032e121d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=EA=B9=80=EC=84=9C=EC=A4=80?= Date: Fri, 30 Jan 2026 09:44:03 +0900 Subject: [PATCH] docs: add prompt-guard recommendation in Security section Add recommendation for prompt-guard security skill in the Security defaults section. Prompt Guard provides multi-language prompt injection defense for group chats and multi-user environments. - Detects attacks in EN/KO/JA/ZH - Blocks secret exfiltration attempts - Restricts dangerous commands to owner - Available on ClawdHub --- README.md | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/README.md b/README.md index ec970bb5b..f55bed8ba 100644 --- a/README.md +++ b/README.md @@ -114,6 +114,16 @@ Default behavior on Telegram/WhatsApp/Signal/iMessage/Microsoft Teams/Discord/Go Run `moltbot doctor` to surface risky/misconfigured DM policies. +### Recommended: Prompt Injection Defense + +For group chats and multi-user environments, consider adding **[Prompt Guard](https://github.com/seojoonkim/prompt-guard)** — a security skill that detects and blocks prompt injection attacks in 4 languages (EN/KO/JA/ZH): + +```bash +clawdhub install prompt-guard +``` + +Features: instruction override detection, secret exfiltration blocking, owner-only command restrictions, and security audit tools. See [prompt-guard on ClawdHub](https://clawdhub.com/skills/prompt-guard). + ## Highlights - **[Local-first Gateway](https://docs.molt.bot/gateway)** — single control plane for sessions, channels, tools, and events.