360 Zhiniao

v0.1.0

提供360智脑公开页面的模型信息、定价和文档摘要,支持内容检索与链接汇总,专注公开数据整理。

0· 188·0 current·0 all-time
byClawKK@codekungfu
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/description claim: gather public model, pricing, and docs info from 360智脑 public pages. Declared requirements: none. There are no unrelated env vars, binaries, or install steps — the requested capabilities match the stated purpose.
Instruction Scope
SKILL.md confines actions to visiting and parsing public pages on https://ai.360.cn/, extracting model/pricing/docs info, and respecting rate limits. It explicitly forbids account operations or API calls. The only implementation ambiguity is that pages are dynamic and require waiting/rendering, which is an implementation detail rather than scope creep.
Install Mechanism
No install spec and no code files — instruction-only skill. Nothing will be downloaded or written by the skill itself during install.
Credentials
The skill declares no environment variables, credentials, or config paths. That aligns with its public-data-only purpose.
Persistence & Privilege
always is false and the skill does not request persistent privileges or to modify other skills. Autonomous invocation is allowed (platform default) but not combined with other concerning factors.
Assessment
This skill appears coherent: it only describes scraping and summarizing publicly accessible pages on ai.360.cn and does not request credentials or installations. Before enabling, consider: (1) you are allowing the agent to access external web pages — ensure you are comfortable with that network activity; (2) the SKILL.md notes pages are dynamic, so a real implementation may require a headless browser or rendering engine (not included here); and (3) scraping should respect robots.txt, rate limits, and the target site's terms to avoid IP blocking or legal issues. If you need guaranteed safeguards (e.g., limit outbound requests or disallow web access), enforce them at the agent/platform level before installing.

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

latestvk97cefmk799h2reaa0gr2g7wxd831rp1

License

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

Comments