Back to skill
Skillv1.0.0
ClawScan security
hanyilong first skill · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 26, 2026, 9:17 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is a simple 'hello world' template skill with a harmless example script and no requests for credentials, installs, or unusual capabilities — it appears internally consistent though it's incomplete as a real skill.
- Guidance
- This skill is essentially a template/hello-world and appears safe: it contains only explanatory text and a tiny Python script that prints a message. Before installing or running it, consider: (1) the SKILL.md is incomplete — the author needs to add concrete behavior; (2) if you plan to run the included script, inspect it yourself (it currently only prints a message); (3) if the skill is later expanded, re-check for network calls, credential requests, or downloads. Because it requests no credentials and has no install steps, risk is low, but always review any code before executing it in your environment.
Review Dimensions
- Purpose & Capability
- okName/description say 'hello world' and the bundle contains only a template SKILL.md and a trivial example Python script that prints a message — the requested resources match the stated purpose.
- Instruction Scope
- noteSKILL.md is a generic template with TODOs and does not instruct the agent to read files, access credentials, or call external endpoints. It is incomplete (no concrete runtime steps), which is not a security problem but means the skill currently does nothing useful until filled in.
- Install Mechanism
- okNo install spec is provided (instruction-only plus a small script). Nothing will be downloaded or written during installation.
- Credentials
- okThe skill declares no required environment variables, credentials, or config paths — proportional for a template/hello-world skill.
- Persistence & Privilege
- okSkill does not request persistent or elevated privileges (always is false). Model invocation is allowed by default, which is normal for skills and acceptable here given the minimal scope.