Back to skill
Skillv0.1.0
ClawScan security
网红奶茶 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignMay 1, 2026, 7:58 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5.5
- Summary
- This is an instruction-only bubble tea recommendation guide with no code, credentials, install steps, or sensitive permissions shown.
- Guidance
- This skill appears low risk from the provided artifacts. Users should still treat restaurant details such as real-time popularity, opening hours, queues, and prices as information to verify before traveling.
Review Dimensions
- Purpose & Capability
- okThe instructions align with the stated purpose of providing bubble tea recommendations, route ideas, and visit guidance.
- Instruction Scope
- okThe skill gives content-format and planning guidance only; it does not instruct the agent to override user intent, run tools, or take actions on the user's behalf.
- Install Mechanism
- okNo install specification, binaries, dependencies, scripts, or code files are present.
- Credentials
- okThe artifacts request no environment variables, credentials, local files, network access, or system capabilities.
- Persistence & Privilege
- okNo persistence, background process, privilege escalation, account access, or stored memory behavior is evidenced.