DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to screen prompts for PII and prompt injection with Antirion

Add guardrails that check requests, responses and streams before models see them.

Who it is forA security or compliance owner whose apps send user text to LLMs and must keep personal data and injection attempts out.

The problemUser text can carry personal data or instructions that try to override the app, and each app would need its own filter.

The outcomeRequests with PII or injection attempts are caught at the gateway, and redaction keeps the original format.

What you need first

  • Docker installed on the machine that will run the gateway
  • An API key from OpenAI or Anthropic
  • A web browser to open the console at http://localhost:8081/ui/

Steps

  1. Start the gateway with docker run -p 8080:8080 -p 8081:8081 -v antirion-data:/var/lib/antirion eliasbiondo/antirion.
  2. In the console, open the guardrail settings and enable the PII and prompt injection checks for the key or project. (inferred, check the README)
  3. Send a test chat request with a made-up email address in the message using the Playground or the curl command from the getting started guide.
  4. Open Request log and confirm the request shows the guardrail result.

Prompt for your agent

Using the eliasbiondo/antirion README, enable the PII guardrail for the key <key name> in the console and send a test request containing a fake email address. Expected output: the request is redacted or blocked as configured. Verify the result in the Request log.

Caveat. The README lists the guardrail types but the exact configuration steps are not in the excerpt, so each step must be checked against the console.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page