Back to skill
Skillv1.0.0
ClawScan security
Santiago · ClawHub's context-aware review of the artifact, metadata, and declared behavior.
Scanner verdict
BenignApr 17, 2026, 3:25 AM
- Verdict
- Benign
- Confidence
- high
- Model
- gpt-5-mini
- Summary
- The skill is an instruction-only travel guide for Santiago, Chile; its requirements and instructions are consistent with that purpose and it requests no credentials or installs.
- Guidance
- This skill appears to be a simple, instruction-only Santiago travel guide and is internally consistent. Before installing, consider: (1) content freshness — travel details can change, so verify critical info (transport, opening hours); (2) language — the SKILL.md is in Chinese, so check it matches the language you want the agent to use; (3) autonomous invocation — the skill can be called by the agent when relevant (default behavior), but it requests no secrets or installs, so risk is low.
Review Dimensions
- Purpose & Capability
- okName and description (Santiago travel guide) match the SKILL.md content. There are no unexpected binaries, env vars, or config paths required.
- Instruction Scope
- okSKILL.md contains city history, attractions, food, and practical info and a small 'read_when' trigger list tying it to travel queries. It does not instruct reading unrelated files, contacting external endpoints, or accessing secrets.
- Install Mechanism
- okNo install spec and no code files — instruction-only skill with no artifacts written to disk. This is the lowest-risk install pattern.
- Credentials
- okThe skill declares no required environment variables or credentials; nothing disproportionate is requested for a travel-guide skill.
- Persistence & Privilege
- okalways is false and the skill does not request persistent system presence or elevated privileges. Autonomous invocation is allowed by default but is normal and not combined with other red flags here.