Secret scanning for AI coding tools

Developers increasingly rely on AI coding tools like Cursor and Claude Code to write and modify code. These tools can inadvertently expose secrets: a developer might paste credentials into a prompt, or the AI agent might read a file or run a command that contains API keys or tokens. Once a secret reaches the AI model, it may be logged, cached, or sent to third-party services.

ggshield integrates with AI coding tools through their hook systems to scan interactions in real time. When a secret is detected, ggshield blocks the action before it reaches the model and tells the developer to remove the secret.

How it works

AI coding tools support hooks: custom commands that run at specific points during an AI interaction. ggshield registers as a hook and scans content at three stages:

Stage	What it does	Behavior
Prompt submission	Scans the user's prompt before it is sent to the AI model	Blocks the prompt if secrets are found
Pre-tool use	Scans commands, file reads, and MCP calls before the AI executes them	Blocks the action if secrets are found
Post-tool use	Scans tool outputs after execution	Sends a desktop notification if secrets are found

ggshield uses the same detection engine as all other scanning commands, covering over 500 types of secrets.

Prerequisites

• ggshield version 1.49.0 or later
• A GitGuardian API key (see Getting started)
• One of the supported AI coding tools: Cursor, Claude Code, or VS Code with GitHub Copilot

Installation

ggshield provides a one-command installer that writes the correct hook configuration for each tool.

Cursor

$ ggshield install -t cursor -m global

This writes hooks to your global .cursor/hooks.json file. To install for the current project only:

$ ggshield install -t cursor -m local

The generated configuration registers ggshield on all three hook stages (prompt submission, pre-tool use, and post-tool use).

Claude Code

$ ggshield install -t claude-code -m global

This writes hooks to your global .claude/settings.json file. To install for the current project only:

$ ggshield install -t claude-code -m local

The generated configuration registers ggshield on all three hook stages (prompt submission, pre-tool use, and post-tool use).

VS Code with GitHub Copilot

$ ggshield install -t copilot -m global

This writes hooks to your global VS Code settings. To install for the current project only:

$ ggshield install -t copilot -m local

The generated configuration registers ggshield on all three hook stages (prompt submission, pre-tool use, and post-tool use).

tip

If you already have hook configurations for the target tool, ggshield merges its hooks into the existing file without touching other hooks. Use --force to overwrite ggshield's own hooks (for example, if they were customized and you want to reset them).

What the developer sees

When ggshield detects a secret, the AI coding tool displays a blocking message. For example, in Cursor:

Detected 1 secret

• Google API Key (valid): AIzaSyC****************-*********d5oii7Y

Please remove the secrets from the content before proceeding.

The prompt or action is blocked until the developer removes the secret and retries.

For post-tool-use detections (where the action already ran), ggshield sends a desktop notification alerting the developer.

Handling false positives

If ggshield blocks an action on a secret that is a known false positive, you can tell ggshield to ignore it:

$ ggshield secret ignore --last-found

This adds the detected secret to your .gitguardian.yaml ignore list. Future scans (including AI hook scans) will skip it.

Uninstallation

To remove the hooks, delete the ggshield entries from the tool's configuration file:

• Cursor: .cursor/hooks.json
• Claude Code: .claude/settings.json
• VS Code with GitHub Copilot: VS Code settings

See also

• ggshield secret scan ai-hook reference: CLI reference for the underlying scan command
• Getting started with ggshield: Installation and authentication