Screen chat messages for GDPR-safe PII and injection with PromptLock Guard and Claude
UnknownUnknown. This template uses community nodes we can't verify statically. Uses community nodes that can't be verified statically (unverified community packages are off by default in 3.0). Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 7 nodes and runs when a chat message arrives. Along the way it connects Promptlock Guard (community). It also calls api.anthropic.com over HTTP.
How it runs
Trigger: When a chat message arrives.
- PromptLock Compliance Guard (Prompt Lock Guard): analyze (prompt)
- Injection Detected? (If): checks a condition and branches into true / false
- Hold for Human Review (Edit Fields (Set)): sets 1 field: output
- Refuse Unsafe Message (Edit Fields (Set)): sets 1 field: output
- Claude Generates Reply (HTTP Request): calls api.anthropic.com (POST)
- Format Chat Reply (Edit Fields (Set)): sets 1 field: output
Services it uses
HTTP calls to: api.anthropic.com
Before you upgrade to n8n 3.0
We can't fully verify this one: it relies on 1 community package, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
- Check that n8n-nodes-promptlock-guard is verified or supports 3.0 (used in PromptLock Compliance Guard).
Nodes used (5)
- Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Prompt Lock Guard
n8n-nodes-promptlock-guard.promptLockGuard - If
n8n-nodes-base.if - HTTP Request
n8n-nodes-base.httpRequest - Edit Fields (Set)
n8n-nodes-base.set
From the author
Quick overview An AI chat assistant that screens every incoming message for personal data and prompt-injection attacks before it reaches the language model. Personal data is redacted, injection attempts are refused, and clean messages pass straight through —…