Back to skill
Skillv0.1.0

ClawScan security

dianping · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignMar 15, 2026, 4:28 AM
Verdict
Benign
Confidence
high
Model
gpt-5-mini
Summary
The skill is an instruction-only assistant for evaluating Dianping listings; its requirements and instructions match its described purpose and it does not request unrelated credentials or install code.
Guidance
This skill appears coherent and does what it claims (help judge Dianping listings). Before using it, decide whether you want the agent to open pages or capture screenshots from your browser — avoid giving login credentials or sharing private pages unless you explicitly want it to inspect logged-in content. Remember that 'benign' here means the skill's behavior matches its description, not that it can't make mistakes; review any recommendations before acting on them.

Review Dimensions

Purpose & Capability
okName/description (Dianping review/deal/store vetting) align with the included reference files and SKILL.md. No unrelated binaries, env vars, or config paths are requested.
Instruction Scope
noteRuntime instructions stay on-topic (review analysis, deal judgment, store comparison). The browser workflow mentions inspecting public pages and using screenshots and restricting logged-in pages to 'user' only when necessary — this is coherent but requires explicit user consent before accessing any logged-in content or capturing screenshots containing personal data.
Install Mechanism
okNo install spec and no code files — instruction-only skill; nothing is written to disk or downloaded during install.
Credentials
okThe skill requests no environment variables, credentials, or config paths. The scope of access implied by the instructions (web page inspection) is proportional to the stated purpose.
Persistence & Privilege
okalways is false and disable-model-invocation is false (normal). The skill does not request permanent presence or elevated system privileges.