Back to skill
Skillv1.0.0
ClawScan security
O · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMar 12, 2026, 11:21 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only helper that suggests short OS-specific 'open' commands and its requirements and instructions are consistent with that purpose.
- Guidance
- This skill is coherent and low-risk: it will suggest short OS-specific 'open' commands. Before running any suggested command, verify the path or URL to avoid opening malicious content. If you allow the agent to invoke skills autonomously, monitor outputs before executing commands in your shell or file explorer.
Review Dimensions
- Purpose & Capability
- okName and description match the content of SKILL.md: it only provides short OS-specific commands to open files, folders, URLs, or repositories. No unrelated credentials, binaries, or config paths are requested.
- Instruction Scope
- okSKILL.md contains only guidelines and example commands for Windows/macOS/Linux and instructs the agent to be brief and respect the user's OS. It does not instruct reading unrelated files, env vars, or sending data to external endpoints. The 'do not perform dangerous operations' guideline is included and appropriate.
- Install Mechanism
- okNo install spec and no code files are present (instruction-only), so nothing is written to disk or installed at runtime.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths; that is proportionate to its simple purpose.
- Persistence & Privilege
- okalways is false and the skill does not request elevated or persistent presence. Autonomous invocation is allowed by default but the skill's scope is narrow.