Detect prompt injection and redact PII in LLM apps. Your client pastes their PromptGuard key once, and your agent or your code works with their access.
AI
About PromptGuard
Through Operate As, your agent, n8n workflow or code works in PromptGuard with your client's own access. Your client pastes their API key from PromptGuard once. We store it encrypted, so it never sits in an email or a shared doc. Your agent reaches any endpoint of PromptGuard's API through the request tool, with the client's access attached.
Common uses in AI
Generate, summarize or classify content inside a workflow
Use the client's own account, billed to them
Combine results with their other connected tools
PromptGuard
PromptGuard · AI
API key
Detect prompt injection and redact PII in LLM apps
The client pastes their API key from PromptGuard's settings. We store it encrypted.
Tested against PromptGuard's live API.
Building with PromptGuard? The docs have setup steps and code for every tool.
Add a client, select the services, copy the link. You'll get an email the moment their access is ready. Start free, no card required. Paid plans are one flat monthly price, and a busy month never takes your agents offline.