Back to skill
Skillv2.1.0

ClawScan security

Metaso Search V2 · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignFeb 11, 2026, 9:29 AM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
The skill's code, instructions, and required environment variable (METASO_API_KEY) are consistent with a search/chat/read API client and do not request unrelated credentials or perform unexpected actions.
Guidance
This skill appears coherent: it requires only METASO_API_KEY and contacts Metaso endpoints (https://metaso.cn). Before installing, confirm you trust the Metaso service and the skill author (repository/homepage is empty), limit the API key's scope if possible, store the key securely, and consider testing in an isolated environment. If you need stronger assurance, ask the publisher for a repository URL or signed package so you can review provenance and updates.

Review Dimensions

Purpose & Capability
okName/description (Metaso search, web reader, chat) match the actual implementation: the code calls Metaso API endpoints and requires only METASO_API_KEY. No unrelated services, binaries, or config paths are requested.
Instruction Scope
okSKILL.md contains focused runtime instructions and example usage that map directly to the implemented functions. It does not instruct reading arbitrary local files, other environment variables, or exfiltrating data to unexpected endpoints.
Install Mechanism
okThere is no install spec (instruction-only install). Code files are provided but no installer or external download is used; risk from install mechanism is low.
Credentials
okOnly METASO_API_KEY is required and used by the code (Authorization header). The number and nature of environment variables is proportional to the stated purpose.
Persistence & Privilege
okSkill is not forced-always, is user-invocable, and does not request elevated/platform-wide privileges or modify other skills' configs. Autonomous invocation is allowed (platform default) and is not combined with other red flags.