Baidu Map

v0.1.0

查询和比较百度地图POI信息及公交驾车路线,支持BD-09坐标标注与转换说明,限量自动化操作。

0· 302·1 current·1 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 (POI, routes, BD-09 coordinates) match the SKILL.md tasks. The skill requests no binaries, env vars, or access beyond public map.baidu.com pages — all proportional to the described functionality.
Instruction Scope
SKILL.md stays within scope: it outlines using public Baidu Map pages, extracting visible fields, route comparisons, and coordinate conversion notes. It explicitly discourages bulk scraping and recommends rate-limiting. The guidance leaves implementation details (how to extract/render/wait/export CSV) to the agent, which is expected for an instruction-only skill but gives the agent discretion that should be monitored to avoid unintended scraping or TOS violations.
Install Mechanism
No install spec and no code files — lowest-risk model for installation (nothing is downloaded or written by the skill itself).
Credentials
No required environment variables, credentials, or config paths are declared. This is proportionate for a skill that works with public web pages.
Persistence & Privilege
always:false and normal autonomous invocation settings. The skill does not request persistent privileges or modify other skills/config; no extra privileges are requested.
Assessment
This skill appears to do what it says: summarize POIs and compare routes from public Baidu Map pages and note coordinate-system differences. Before installing, consider: (1) the agent will have discretion to perform web interactions and export results (e.g., CSV)—monitor or restrict automated runs if you want manual approval; (2) follow Baidu's Terms of Service and the SKILL.md advice on rate-limiting (≥10s/request) to avoid account or IP risk; (3) there are no credentials requested, so no secret-exfiltration risk from the skill itself, but ensure the agent isn't given unrelated credentials that could be used while running; (4) because implementation details are left to the agent, watch for any runaway bulk-scraping behavior in practice.

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

latestvk972kee48pf3k7gchrezbbc2xh8313rb

License

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

Comments