Sensitive Canary

Sensitive Canary

[](https://github.com/coo-quack/sensitive-canary/actions/workflows/ci.yml) [](https://opensource.org/licenses/MIT)

A security plugin that prevents unintended data leaks from Claude Code. Automatically detects and blocks secrets and PII — in prompts, file reads, and command executions — before they are sent to the Anthropic API.

No proxy server. No background process. Native Claude Code hooks only.

📖 **[Documentation](https://coo-quack.github.io/sensitive-canary/)** — Installation guide, detection rules reference, and allow tag details.

---

Why sensitive-canary?

Claude Code is a powerful development tool, but file reads and command executions can inadvertently send secrets and personal information to the Anthropic API. API keys in `.env` files, tokens embedded in config files, credentials pasted into the terminal — once sent to the API, they leave your machine.

**sensitive-canary intercepts them before they are sent, preventing unintended data leaks.**

Without sensitive-canary	With sensitive-canary
cat .env → full contents sent to Claude ❌	Blocked by name before Claude reads it ✅
Paste a live AWS key in a prompt ❌	Blocked before the API call is made ✅
Read customers.csv full of email addresses ❌	PII detected before Claude sees the file ✅
echo $API_KEY with live key ❌	Env var value scanned and blocked ✅
cat docker-compose.yml with POSTGRES_PASSWORD: ❌	Assignment detected in YAML and JSON too ✅

• Two hooks — UserPromptSubmit and PreToolUse cover both directions of risk
• 76 detection rules — sourced from gitleaks and TruffleHog detector definitions
• Checksum validation — credit cards (Luhn) and national ID numbers (JP My Number, FR NIR, IT Codice Fiscale, DE S