Skip to content
TrustedSkillsbeta
Back to all skills

Airlock

Checked
rustydotwtf·vlatest·security·MIT

Airlock safely copies and pastes content between different contexts, preventing data loss and streamlining workflows for complex tasks.

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 whetstoneresearch/doppler-skills --skill airlock -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

rustydotwtf

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 rustydotwtf/doppler-skills at 4f654fea1f.

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

Commit
4f654fea1f
Manifest
skills/airlock/SKILL.md
Scanned
3 files, 137 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

The airlock skill provides a mechanism to isolate and control access to specific resources or processes within an AI agent's environment. It allows for creating secure containers, preventing unauthorized interactions, and managing dependencies between different components of the agent’s workflow. This enhances security and stability by limiting potential damage from errors or malicious actions.

When to use it

  • Sandboxing experimental code: Isolate new plugins or scripts to prevent them from impacting core system functionality during testing.
  • Managing sensitive data access: Restrict access to API keys, credentials, or personal information to only necessary components.
  • Creating isolated workflows: Separate distinct tasks (e.g., web scraping vs. data analysis) into independent environments with specific permissions.
  • Controlling external tool interactions: Limit the actions an agent can perform when interacting with third-party services.

Key capabilities

  • Resource isolation
  • Access control management
  • Dependency containment
  • Secure containerization

Example prompts

  • "Create a sandboxed environment for running this Python script."
  • "Restrict access to the OpenAI API key to only the summarization module."
  • "Isolate the web scraping process into its own container with limited network access."

Tips & gotchas

The airlock skill may require specific permissions or configurations within the agent's environment. Ensure that the underlying system supports containerization and resource isolation for optimal functionality.