catl

v0.1.0

Information assistant for 宁德时代 CATL. Search products, news, financials, and official resources for 宁德时代 CATL.

0· 36·0 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
The name and description (CATL information assistant) match the SKILL.md instructions. The skill only requires web search access to public sources; there are no unrelated environment variables, binaries, or configuration paths requested.
Instruction Scope
Runtime instructions are narrow and explicit: identify the user's query, use web search tools, prioritize the official site, and present results with source links. The instructions do not ask the agent to read local files, access secrets, or transmit data to unexpected endpoints.
Install Mechanism
No install spec and no code files (instruction-only). This is the lowest-risk pattern: nothing is written to disk or pulled from external URLs by the skill itself.
Credentials
The skill declares no required environment variables, credentials, or config paths. Mentioning financial data providers is reasonable for the stated purpose; the skill does not request API keys or secrets.
Persistence & Privilege
always is false and the skill does not request elevated or permanent presence. Default autonomous invocation is allowed by the platform but the skill's scope does not amplify risk.
Assessment
This skill appears coherent and low-risk: it only performs web searches for public CATL information and asks for no credentials or installs. Before installing, consider: (1) the author/source is unknown — if provenance matters, prefer skills with a verifiable homepage or publisher; (2) the agent will query external sites, so avoid submitting any private or sensitive data in queries (searches may be sent to third-party services); (3) verify financial facts from primary/official filings before making any financial decisions; (4) if you want tighter control, keep autonomous invocation restricted or review the agent's browsing/network logs when the skill runs.

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

latestvk97d9kbbw86a1yatcnga7d3qfh842x9w

License

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

Runtime requirements

🏢 Clawdis

Comments