Back to skill
Skillv1.0.0
ClawScan security
Beijing City · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 25, 2026, 9:02 PM
- Verdict
- benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is a purely informational, instruction-only document about Beijing; its declared purpose matches its content and it requests no credentials, installs, or system access.
- Guidance
- This skill is informational and appears safe: it doesn't request credentials, install anything, or access local files. If you plan to rely on the data (population, GDP, counts of universities, etc.), verify the figures against an authoritative source because the SKILL.md is static and the source is unknown. Otherwise it's low-risk to install/use.
Review Dimensions
- Purpose & Capability
- okThe name/description (Beijing city facts) align with the SKILL.md content (history, economy, facts). There are no unexpected required binaries, env vars, or config paths.
- Instruction Scope
- okSKILL.md contains only static descriptive content and a short 'read_when' usage list. It does not instruct the agent to read local files, access environment variables, run commands, or transmit data to external endpoints.
- Install Mechanism
- okNo install spec and no code files are present; this is instruction-only and does not write to disk or fetch external code.
- Credentials
- okThe skill requests no environment variables, credentials, or config paths — consistent with its informational purpose.
- Persistence & Privilege
- okalways is false and the skill does not request elevated persistence or modify other skill/system settings. Autonomous invocation is allowed by default but is not a concern here because the skill has no side-effecting instructions.