LLM-Sentinel: Shield your AI calls from leaking secrets

Raihan Kabir — Mon, 01 Sep 2025 06:26:02 +0000

Every day, API keys, tokens, emails, and DB URLs slip into prompts, logs, or demos. Once they hit the LLM, they’re out of your control.

I built LLM-Sentinel, a privacy-first proxy that:

Intercepts requests to OpenAI, Ollama, Claude, etc.
Masks 52 types of sensitive data (API keys, creds, emails, credit cards, SSNs).
Works with streaming, adds no noticeable latency (1-3ms).
Comes with a real-time dashboard to watch what’s being masked.
Zero data retention. All secrets stay local.

How it works:
Swap your SDK base URL:

client = openai.OpenAI(
  api_key="sk-...",
  base_url="http://localhost:5050/openai/v1"
)

# Input: My AWS key is AKIA... and email user@company.com
# Model sees: My AWS key is [AWS_ACCESS_KEY_MASKED] and email [EMAIL_MASKED].

Install:

npm install -g llm-sentinel

llmsentinel help

or run via Docker:

docker pull raaihank/llm-sentinel:latest

docker run -p 5050:5050 raaihank/llm-sentinel:latest

Repo: github.com/raaihank/llm-sentinel

Feedback and contributions welcome. If you find this useful, drop a ⭐ on GitHub.

DEV Community: Raihan Kabir

LLM-Sentinel: Shield your AI calls from leaking secrets