crrc

v0.1.0

Information assistant for 中国中车 CRRC. Search products, news, financials, and official resources for 中国中车 CRRC.

0· 31·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name and description describe an information assistant for 中国中车 (CRRC). The skill requests no binaries, env vars, or config paths and does not attempt to access unrelated systems — the resources it asks for are proportionate to a web-search-based info assistant. Note: the skill's source/homepage is not provided in registry metadata (author listed in SKILL.md), so provenance is limited but this does not create an internal inconsistency.
Instruction Scope
SKILL.md instructs the agent to identify the user's CRRC query, use web search tools prioritizing the official site, and present results with links. The instructions do not direct reading local files, accessing unrelated environment variables, or transmitting data to unexpected endpoints. 'Web search tools' is somewhat generic but appropriate for this type of skill.
Install Mechanism
This is an instruction-only skill with no install spec and no code files — lowest-risk installation surface; nothing is written to disk or fetched during installation.
Credentials
The skill declares no required environment variables, credentials, or config paths. That is proportionate for a read-only web-search information assistant.
Persistence & Privilege
always: false and no special privileges requested. The skill can be invoked autonomously per platform default, which is normal for skills; there is no permanent presence or modification of other skills/configs.
Assessment
This skill appears internally consistent and low-risk: it only asks the agent to perform web searches and cite official sources, and it doesn't request credentials or install code. Before installing, consider that (1) the registry metadata lacks a homepage and provenance is limited — if you require verified authorship prefer skills with a clear homepage or organization; (2) the agent will access external websites to answer queries, so avoid submitting sensitive credentials or private data in queries (web requests can be logged by third-party sites); and (3) the skill relies on live web data, which can be inaccurate or change over time. If you need authenticated/privileged company data (private docs, paid financial feeds), verify how credentials would be handled or use an officially supported integration.

Like a lobster shell, security has layers — review code before you run it.

latestvk974ckdx1c2tdpwjedtp35zjnh846v4b

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Runtime requirements

🏢 Clawdis

Comments