Back to skill
Skillv1.0.0
ClawScan security
Video Optimization Specialist · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 12, 2026, 9:52 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill's instructions, files, and requirements match its stated purpose (video optimization guidance) and it does not request credentials, install software, or perform hidden actions.
- Guidance
- This skill is an instruction-only consultant: it provides templates, strategies, and step-by-step advice but cannot act on your YouTube account or fetch analytics without you providing credentials or data. Before handing over any API keys, OAuth tokens, or account exports, confirm you trust the skill's origin (the package lists a GitHub repo in its description but no homepage). If you plan to give it channel analytics or logs, sanitize or limit the data to what's necessary (e.g., share anonymized retention graphs rather than full account credentials). Overall the package is internally consistent and low-risk as-is.
Review Dimensions
- Purpose & Capability
- okName/description and all included files (SKILL.md, AGENTS.md, IDENTITY.md, SOUL.md) consistently describe a video optimization consultant. Nothing in the package requests unrelated resources (cloud credentials, system binaries, or platform tokens) that would be disproportionate to this purpose.
- Instruction Scope
- okSKILL.md and AGENTS.md contain text-only guidance (strategy, templates, workflows) for YouTube and short-form platforms. The instructions do not direct the agent to read local files, access environment variables, call external endpoints, or exfiltrate data.
- Install Mechanism
- okThere is no install spec and no code files — this is an instruction-only skill, so nothing is written to disk and no packages or binaries are fetched.
- Credentials
- okThe skill declares no required environment variables, no primary credential, and no config paths. That matches the content, which is purely advisory and does not need secrets or platform access.
- Persistence & Privilege
- okThe skill is not marked always:true and uses default model-invocation behavior. It does not request elevated persistence or modify other skills or system-wide settings.