Skillv1.0.0

ClawScan security

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

BenignApr 29, 2026, 9:05 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: This is an instruction-only, Chinese-language encyclopedia skill about Amsterdam; it requests no credentials, installs nothing, and its instructions are limited to providing factual content — the pieces are internally coherent.
Guidance: This skill is essentially a static encyclopedia entry about Amsterdam and appears safe to install from a security perspective: it asks for no credentials, installs nothing, and its instructions are limited to content use. Consider these practical points before installing: (1) the factual claims (GDP, population, visitor counts, historical assertions) are approximate — verify against authoritative sources if you need accuracy; (2) the skill is Chinese-language — if you need another language, request/translate accordingly; (3) the agent can still invoke the skill autonomously by default (normal behavior); if you prefer to restrict autonomous use, disable model invocation or configure agent permissions. Overall there are no security red flags in the provided files.

Purpose & Capability: okName, description, and SKILL.md all describe the same purpose (encyclopedic city guide). The skill requests no binaries, env vars, or config paths, which is proportionate to an informational skill.
Instruction Scope: okSKILL.md contains static content and 'read_when' triggers describing when to use the content. It does not instruct the agent to read local files, access other services, exfiltrate data, or call external endpoints.
Install Mechanism: okNo install spec and no code files are present (instruction-only). Nothing is written to disk or downloaded during install.
Credentials: okThe skill declares no required environment variables or credentials; there are no hidden requests for secrets in the instructions.
Persistence & Privilege: okalways is false and disable-model-invocation is default (agent may invoke autonomously), which is normal and not excessive for this type of skill.