ClawHub

Wechat Collect

v1.0.0

Fetch a public WeChat article URL, archive the raw HTML, and convert the article into a stage-1 compatible brief in `content-production/inbox/`. Use when Cod...

⭐ 0· 57·1 current·1 all-time
by@abigale-cyber
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, SKILL.md, README, runtime.py, and skill.json consistently implement a collector that fetches a public mp.weixin.qq.com URL, extracts title/author/date/paragraphs, writes a brief and archives HTML. No unrelated credentials, binaries, or config paths are requested.
✓
Instruction Scope
Runtime instructions and code limit activity to: read an input file for a URL, fetch that URL (including an optional browser fallback for captcha), parse HTML, and write brief/archive files under content-production/inbox. There are no instructions to read unrelated system files, access other services, or transmit data to endpoints beyond the fetched article URL.
ℹ
Install Mechanism
The skill is instruction-only (no install spec). README documents an optional Playwright/browser install for captcha fallback; this is not installed automatically by the skill. This is reasonable for the task, but users should be aware that enabling the browser fallback requires installing npm/playwright components outside the skill.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. The runtime only uses workspace-relative paths (.cache) and writes outputs to the declared inbox/archive directories — proportional to the stated function.
✓
Persistence & Privilege
always is false and the skill does not request permanent platform presence or modify other skills. It writes files into its workspace/inbox and archive directories only, which is expected behavior for a collector.
Assessment
This skill appears coherent and limited to collecting public WeChat articles. Before installing, consider: (1) it will fetch arbitrary public URLs you provide and will write raw HTML into content-production/inbox/raw/wechat — treat those archives as potentially sensitive and store them appropriately; (2) there is an optional browser fallback (browser_fetch_html) that may open an interactive browser to solve captchas — enabling that requires installing Playwright/npm per the README and may create a browser profile under the workspace .cache directory; review how the browser fallback is implemented in skill_runtime.wechat_access if you are concerned about cookie/profile usage; (3) the skill imports helper functions from skill_runtime.wechat_access which are not included here — inspect that module for any unexpected network calls or telemetry if you want higher assurance. If you only provide public article URLs and do not enable the browser fallback, the skill's behavior is limited and proportionate to its purpose.

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

latestvk97c52ex5wv45jbdb0vdk8fdnn84c9e5

License

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

Comments