# Shipped esys-watch to PyPI — Local CLI for LLM Input Safety (Secrets, PII & Prompts)

> Source: <https://discuss.huggingface.co/t/shipped-esys-watch-to-pypi-local-cli-for-llm-input-safety-secrets-pii-prompts/179106#post_1>
> Published: 2026-08-21 23:24:39+00:00

Shipped `esys-watch`

to PyPI — a local CLI that scans text for secrets, PII, and prompt injection patterns before it gets pasted into an LLM.

**Why:** as more of us route logs/code/docs through ChatGPT, Claude, Cursor etc, the leak surface is the copy-paste itself, not just the API layer. This runs entirely local, no account, nothing sent anywhere.

Bash

```
pip install esys-watch
esys-watch --demo
```

Validated against 320 labeled cases (100% recall, 0% FP), plus adversarial testing for ReDoS, malformed input, and concurrent file access.

Open source (MIT), still v0. If anyone here works on LLM security / prompt injection detection, I’d love feedback — especially on where the regex-based injection detection falls short (it’s intentionally scoped to classic patterns only, not multi-turn or indirect injection yet).