Back to skill
Skillv1.0.0
ClawScan security
Hello World · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignFeb 17, 2026, 7:56 AM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- This is a simple, instruction-only greeting skill whose requirements and instructions are consistent with its stated purpose.
- Guidance
- This skill is low-risk: it only instructs the agent to generate greetings and to include the current date/time and an emoji. If you care about timezone formatting or language detection, verify the agent's locale/timezone behavior; otherwise it's safe to install. No credentials or downloads are required.
Review Dimensions
- Purpose & Capability
- okThe name/description match the runtime instructions: producing a localized, personalized greeting with date/time and an emoji. No unrelated credentials, binaries, or config paths are requested.
- Instruction Scope
- okSKILL.md only instructs the agent to produce greetings, include current date/time, an emoji, and personalize when a name is provided. These actions are within scope; the only external data implied is the system clock and the user's language inferred from the user input.
- Install Mechanism
- okNo install spec and no code files — instruction-only. Nothing is written to disk or downloaded during install.
- Credentials
- okNo environment variables, credentials, or config paths are requested. The skill does not ask for elevated access or unrelated secrets.
- Persistence & Privilege
- okalways is false and the skill does not request persistent presence or modify system/agent-wide settings. Normal autonomous invocation is allowed but not required by the skill's behavior.