Skip to content
vibespell

.cursor/rules/security.mdc

Cursor security rule for LangChain

A focused Cursor `.mdc` rule for auth, secrets, and untrusted input. It attaches when those files change, instead of repeating security policy in every chat. This copy is written for a LangChain project. This repository builds LLM agents or chains. Model names and prompts are explicit. Tool calls validate their arguments. API keys stay in the environment.

The example uses a balanced, readable style, pragmatic tests, and comments only where the intent is not obvious. Open the generator to make the agent stricter, switch to test-first, quiet the comments, or pick a different file.

The example assumes a Python agent stack such as LangChain or a similar orchestrator already in the repo. It does not assume LangGraph versus a simple chain, or a hosted tracer. Use what the project already imports.

Customize in the generatorBrowse the library

Example file

Balanced strictness, readable style, pragmatic tests. Download name: security.mdc

---
description: "Security rules for a LangChain repository"
globs: "**/*{auth,Auth,secret,config,Config}*"
alwaysApply: false
---

# Security rules

Attach these rules when editing auth, config, or secret-handling code in this LangChain repository.
This repository builds LLM agents or chains. Model names and prompts are explicit. Tool calls validate their arguments. API keys stay in the environment.

## Secrets and trust

- API keys stay in the environment.
- Tools enforce an allowlist of paths, URLs, or commands.
- Do not send secrets or raw personal data to the model provider.

## Errors

- Fail at the boundary. Do not swallow errors.
- Return a structured tool error the model can read. Unexpected exceptions should fail the call, not invent an answer.

## Done when

- Untrusted input is validated before a side effect.
- No secret was added to source, logs, or a client bundle.
- `pytest` passes, including a test that a bad tool argument does not reach the side effect.

Add it to the project

  1. 01

    Copy a starting file

    Copy the example Cursor security rule on this page, or open the generator if you want different testing, strictness, or comment rules.

  2. 02

    Save it at .cursor/rules/security.mdc

    Save it at `.cursor/rules/security.mdc` in the LangChain repo. Narrow the globs if your auth and config files live in a known folder.

  3. 03

    Start a fresh agent session

    Rules files are read when a session starts. A chat that is already open may still be using the old instructions.

  4. 04

    Give it one small task

    Ask for one change a LangChain agent often gets wrong, such as a tool whose arguments are validated before it touches the filesystem or the network. If it ignores the file, confirm the path and start a new session.

Questions about this file

Where do I put Cursor security rule in a LangChain repo?

Save it at `.cursor/rules/security.mdc` in the LangChain repo. Narrow the globs if your auth and config files live in a known folder.

Which tools read this Cursor security rule?

Cursor loads `.cursor/rules/security.mdc` for files that match its globs. Pair it with the always-on project rule. It is not a substitute for code review.

What does the LangChain example assume?

The example assumes a Python agent stack such as LangChain or a similar orchestrator already in the repo. It does not assume LangGraph versus a simple chain, or a hosted tracer. Use what the project already imports.

Does VibeSpell upload my repository?

No. Recipe pages are static, and the generator builds the file in your browser from the options you pick. Your source code never leaves the machine.

Other files for LangChain

Cursor security rule for other stacks