Skillv1.0.0

ClawScan security

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

BenignApr 28, 2026, 6:05 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is a local, instruction-only historical/summary skill about RadioShack with no installs, no requested secrets, and no instructions that go beyond its stated purpose.
Guidance: This skill is an informational, read-only summary in Chinese about RadioShack and appears safe to install from a permissions perspective. Consider: (1) the content is static prose—if you need citations or up-to-date facts, ask for sources or verify independently; (2) because it contains no code or external calls, risk is low, but also the skill cannot update itself or fetch live data. If you want automatic sourcing or live market data, expect a different skill that would need network access or API credentials.

Purpose & Capability: okThe skill's name, description, and SKILL.md all describe a historical/business summary of RadioShack. It requires no binaries, env vars, or config paths, which is proportionate to an informational skill.
Instruction Scope: okSKILL.md contains static content (overview, timeline, analysis) and a short read_when list for contexts in which the agent should read it. It does not instruct the agent to run shell commands, access files outside itself, read environment variables, or send data to external endpoints.
Install Mechanism: okThere is no install spec and no code files; this is instruction-only so nothing will be written to disk or downloaded during installation.
Credentials: okThe skill declares no required environment variables, credentials, or config paths. No hidden or undeclared credential access appears in the instructions.
Persistence & Privilege: okThe skill is not marked always:true and uses normal user-invocable/autonomous-invocation defaults. It does not request persistent system-wide privileges or attempt to modify other skills or agent configuration.