ClawHub

Skills of A-share market data released by ft.tech.

v1.0.0

非凸科技A股市场数据技能集。覆盖 A 股股票列表、实时行情、IPO信息、大宗交易、融资融券、个股详情与估值等接口。

⭐ 58· 625·0 current·0 all-time
by@shawn92
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 skill name/description describe A‑share market data and the code implements exactly that: each sub-skill issues GET requests to the documented endpoints. One sub-skill intentionally uses a different host (https://ftai.chat) and the SKILL.md explicitly calls this out, so the extra domain is explained.
✓
Instruction Scope
Runtime instructions direct the agent to run run.py which subprocesses the per-subskill handler scripts. The handlers only build URLs and perform urllib HTTP GETs, parse JSON, and print results. They do not read local files, read environment variables, or transmit data to any endpoints beyond the documented domains.
✓
Install Mechanism
There is no install spec (instruction-only), and the packaged code contains only small Python scripts. Nothing is downloaded or installed at runtime; handlers use the standard library for HTTP requests.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths and the code does not access such secrets. The requested privileges are proportional to a read-only market-data skill.
✓
Persistence & Privilege
always is false; the skill is user‑invocable and allows autonomous invocation (disable-model-invocation: false), which is the platform default. There is no request for permanent system presence or modification of other skills/config.
Assessment
This skill appears to be a straightforward market-data wrapper that issues HTTP GETs to https://market.ft.tech and one endpoint at https://ftai.chat and returns JSON. Before installing, confirm you trust those domains and the skill author (source/homepage unknown). If you operate in a sensitive environment, consider running the code in a sandbox or behind network controls so you can observe outbound requests. Because the skill can be invoked autonomously by the agent (platform default), be aware it may make network calls when used by automated flows; no credentials or local files are accessed by the scripts.

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

latestvk9784bmsg990dm33t4cb76yf9n82p36r

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments