ClawHub

XCrawl Scraper

v1.0.0

XCrawl - AI-Powered Web Scraping API / AI 驱动网页爬虫，支持结构化数据提取

⭐ 0· 318·0 current·0 all-time
by@zhangss110
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 match the actual behavior: the files implement a Python client wrapper that calls an external XCrawl API (scrape/search/map/crawl). Required binaries (python, pip) and the xcrawl SDK are appropriate for a Python scraper client.
✓
Instruction Scope
SKILL.md instructs installing the xcrawl SDK, configuring an API key, and running the included script. The runtime instructions and the script only access the included config.json and the XCrawl network endpoint (apiUrl). The instructions do not attempt to read unrelated host files or environment variables.
ℹ
Install Mechanism
There is no automated install spec; SKILL.md recommends pip install xcrawl. Using pip is typical for Python SDKs but carries the usual supply‑chain risk of third‑party packages—verify the 'xcrawl' package source (PyPI/GitHub) before installing.
✓
Credentials
No environment variables or unrelated credentials are requested. The only secret is an API key that the user explicitly sets via the provided set-key command and which is stored in scripts/config.json — behaviour consistent with a cloud scraping API client.
✓
Persistence & Privilege
The skill is not always-enabled and does not request elevated or cross-skill configuration. It persists only its own API key into scripts/config.json; autonomous invocation of the skill by the agent is allowed (platform default) but not excessive given the skill's function.
Assessment
This skill appears to be what it says: a client wrapper for the XCrawl scraping API. Before installing or running it: 1) Verify the xcrawl Python package (source repository, PyPI record) to ensure you trust the package and author; 2) Be aware the scraper sends page data to the XCrawl service (apiUrl run.xcrawl.com) — avoid using it with credentials or pages containing sensitive personal or proprietary data unless you trust the provider and its privacy policy; 3) The API key you set is stored in scripts/config.json inside the skill directory—treat it like any secret and don't check it into public repositories; 4) Installing via pip pulls third‑party code (supply‑chain risk), so prefer inspecting the package source first; 5) Confirm that crawling targets comply with terms of service and robots.txt. If you want extra assurance, review the xcrawl SDK source code and the network endpoints it contacts before use.

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

aivk972d85d515x8pmqmzpaf4k4mx83nx42jsonvk972d85d515x8pmqmzpaf4k4mx83nx42latestvk972d85d515x8pmqmzpaf4k4mx83nx42markdownvk972d85d515x8pmqmzpaf4k4mx83nx42scrapervk972d85d515x8pmqmzpaf4k4mx83nx42web-scrapingvk972d85d515x8pmqmzpaf4k4mx83nx42

License

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

Runtime requirements

🕷️ Clawdis
Binspython, pip

Comments