Skip to content
TrustedSkillsbeta
Back to all skills

Claude Security Settings

Checked
laurigates·vlatest·ai-ml·MIT

Configure Claude's safety settings (e.g., refusal rates, content filters) to align with your organization’s risk tolerance.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add laurigates/claude-plugins --skill claude-security-settings -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

laurigates

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned laurigates/claude-plugins at 45d1d7dcf6.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
45d1d7dcf6
Manifest
configure-plugin/skills/claude-security-settings/SKILL.md
Scanned
1 file, 352 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill allows you to configure Claude Code's security settings, including granular permissions for shell commands and protections against potentially dangerous shell operators. It enables organizations to align Claude Code’s access with their specific risk tolerance by controlling which commands can be executed and preventing the use of risky shell constructs. The configuration is managed through JSON files at different scopes (user, project, local project) with varying priority levels.

When to use it

  • You need to restrict what shell commands Claude Code can execute within a project.
  • Your organization requires specific controls over command execution for security compliance.
  • You want to prevent the use of potentially dangerous shell operators (like &&, ||, or redirection) during code execution.
  • You are managing multiple projects with different security requirements.

Key capabilities

  • Permission Wildcards: Define granular access control using wildcard patterns for Bash commands (e.g., Bash(git status *)).
  • Shell Operator Protections: Prevents the use of dangerous shell operators like &&, ||, ;, and redirection (>, >>) to mitigate command injection risks.
  • Permission Tiers: Control command execution with "allow," "ask" (prompt for confirmation), or "deny" permissions.
  • Scoped Configuration: Manage settings at the user, project (committed), and local project (gitignored) levels, with priority-based overrides.

Example prompts

  • “Set up Claude Code to allow git status but deny rm -rf *.”
  • "Configure permissions so that running npm run build requires confirmation."
  • "What is the highest priority settings file for controlling Bash commands?"

Tips & gotchas

  • Settings are applied based on a priority system: Local project > Project level > User level.
  • Be mindful of wildcard patterns; overly broad patterns can unintentionally grant excessive permissions.
  • Claude Code 2.1.7 and later versions include built-in protections against dangerous shell operators, which will trigger explicit approval prompts if encountered.