YouTube Shorts Agent

AdvisoryAudited by Static analysis on May 6, 2026.

Overview

No suspicious patterns detected.

Findings (0)

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

A mistaken live upload could publish or modify content on a YouTube channel.

Why it was flagged

The skill can trigger YouTube uploads, which are high-impact account actions, but the artifact clearly requires user ownership, explicit intent, and final confirmation.

Skill content
Use only for user-owned channels and media. Never upload without explicit user intent and final confirmation.
Recommendation

Start with connection_status, privacy_audit, manifest, and dry-run workflows, and require a clear final confirmation before any live upload.

What this means

OAuth access could allow the tool to act on the connected YouTube account within the granted scopes.

Why it was flagged

The skill expects access to YouTube-related credentials or token files; this is proportionate to the upload purpose, but users should treat it as sensitive account authority.

Skill content
Do not print OAuth tokens, API keys, service-account JSON, local token files, or private user data.
Recommendation

Grant only the minimum YouTube scopes needed, keep tokens private, and revoke access if the package is no longer needed.

What this means

Users are trusting the current npm package contents, which were not included in the provided artifact set.

Why it was flagged

The setup downloads and runs an external npm package with automatic yes behavior and no pinned version in the skill artifact; this is normal for MCP setup but depends on npm package provenance.

Skill content
`npm exec --yes --package=youtube-shorts-agent -- youtube-shorts-agent doctor`
Recommendation

Verify the npm package and repository, consider pinning a trusted version, and review the package before connecting OAuth credentials.