This skill informs the agent how to use Viam CLI

WarnAudited by ClawScan on May 10, 2026.

Overview

This is a legitimate-looking Viam CLI guide, but it gives the agent broad power over robots, cloud data, deployments, and API keys with limited approval and scoping guidance.

Install only if you want the agent to help administer Viam resources. Before using it, set a rule that the agent must ask before every command that changes robots, datasets, cloud data, modules, API keys, databases, or pipelines, not just delete commands. Use a least-privileged Viam profile and avoid sharing API keys in chat.

Findings (4)

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 used too freely, the agent could change or disrupt robots, move files to or from machines, deploy/restart modules, or modify cloud data beyond what the user intended.

Why it was flagged

The skill exposes broad, high-impact CLI operations: remote shell, remote file copy, module deployment/restart, and cloud data deletion. These are aligned with Viam administration, but the instructions only explicitly require confirmation for delete commands, leaving other high-impact operations insufficiently bounded.

Skill content
`viam machines part shell --organization=<org> --location=<loc> --machine=<id>` ... `viam machines part cp` ... `viam module reload --part-id <machine-part-id>` ... `viam data delete tabular`
Recommendation

Require explicit user approval before every mutating Viam command, especially remote shell, file copy, module reload/upload, API key creation, database configuration, data tagging, dataset changes, and pipeline enable/disable.

What this means

A generated or mishandled Viam API key could grant programmatic access to robotics resources beyond the immediate task.

Why it was flagged

The skill documents both API-key authentication and creation of new machine-part API keys. Although it warns not to paste credentials into chat, it does not define approval, scoping, storage, rotation, or revocation controls for newly created credentials.

Skill content
`viam login api-key --key-id <id> --key <secret>` ... `viam machines api-key create` - Generates a new machine part API key for programmatic access.
Recommendation

Use the least-privileged Viam account/profile, avoid handling secrets in chat, and require explicit user approval plus clear scope and revocation steps before creating any API key.

What this means

A mistaken module reload or deployment could interrupt a robot or cause operational problems on connected machines.

Why it was flagged

Deploying and restarting modules on a robotics machine can propagate a bad local change into a live remote system. The artifact does not describe staging, rollback, dry-run, or explicit confirmation requirements for this non-delete deployment action.

Skill content
`viam module reload --part-id <machine-part-id>` - **(Hot Reloading)** Bundles local module code, deploys it to the target machine via WebRTC, registers it as a local module, and restarts it.
Recommendation

Use staging machines where possible, require explicit confirmation before deploy/restart commands, record the target machine part, and provide rollback instructions before proceeding.

What this means

Installing the CLI changes the local system and depends on the Homebrew tap source being trustworthy.

Why it was flagged

The skill instructs installing the Viam CLI from a Homebrew tap after user approval. This is disclosed and purpose-aligned, but users should recognize it adds external software to the local environment.

Skill content
`brew tap viamrobotics/brews` ... `brew install viam`
Recommendation

Approve installation only if you trust the Viam Homebrew source, and verify the installed CLI version before using it with your account.