zx

ReviewAudited by ClawScan on May 4, 2026.

Overview

This is an instruction-only reference for Google zx; it discusses powerful shell and remote execution features, but the behavior is disclosed and aligned with its stated scripting purpose.

This skill appears to be a benign zx reference. Install it if you want the agent to help write zx scripts, but remember that zx scripts are shell scripts with full local command power. Review commands, avoid untrusted remote scripts, and pin packages when using npx or auto-install features.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

If the agent uses this guidance to create or run scripts, shell commands may have real effects on your computer or projects.

Why it was flagged

The skill teaches use of zx's shell-command execution API. This is expected for a zx scripting guide, but commands can modify files, deploy code, or affect the local environment if run without review.

Skill content
### `` $`command` `` — Execute Shell Commands
Recommendation

Review generated zx commands before running them, especially commands that write files, install packages, deploy, delete, or change configuration.

What this means

A script run with auto-install can fetch and execute third-party packages, which may affect your environment if the package or registry is untrusted.

Why it was flagged

The CLI reference documents zx's ability to auto-install missing dependencies. This is a legitimate zx feature, but it can introduce package-supply-chain risk if used with untrusted scripts or unpinned dependencies.

Skill content
zx --install script.mjs
Recommendation

Prefer pinned dependency versions, trusted registries, and review dependency imports before using zx's auto-install feature.

What this means

Running a remote zx script can execute code from the internet on your machine.

Why it was flagged

The documentation explains that zx can execute remote scripts. The artifact also warns users to trust the source, so this is disclosed and purpose-aligned, but remote script execution is high-impact if misused.

Skill content
Scripts starting with `https://` are downloaded and executed.
Recommendation

Only run remote zx scripts from sources you trust, inspect the script first when possible, and avoid piping or executing unknown URLs.