Skillv1.0.0

ClawScan security

Liuzln Openclaw Skills Wechat Article Fetcher · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignApr 14, 2026, 5:39 PM

Verdict: benign
Confidence: high
Model: gpt-5-mini
Summary: The skill's code, instructions, and requirements are consistent with a WeChat article scraper: it uses Playwright to load pages, download images, take screenshots, and save JSON without requesting unrelated credentials or contacting unexpected endpoints.
Guidance: This skill appears to do what it says (scrape WeChat article pages using Playwright). Before installing or running: (1) install Playwright and the browser (pip install playwright; playwright install chromium) in an isolated virtualenv; (2) review and, if needed, change the VENV_PATH default in fetch_direct.py if you use that helper (it defaults to /opt/playwright-env); (3) be aware the scripts write files (screenshots, images, JSON) into local directories—store them in an appropriate location and avoid running as root; (4) respect site terms and robots.txt when scraping; and (5) if you need higher assurance, run the code in a disposable environment and inspect network activity during a test run.

Review Dimensions

Purpose & Capability: okName/description match the included files and behavior: scripts and modules implement page loading, content extraction, image download, screenshots, and JSON export for mp.weixin.qq.com articles. No unrelated services or credentials are requested.
Instruction Scope: okSKILL.md and the code instruct the agent to run local Python scripts and Playwright to visit WeChat article URLs, extract DOM content, download images, and write local files. The instructions do not ask the agent to read unrelated system files, exfiltrate data to external endpoints, or access other credentials.
Install Mechanism: noteNo install spec is provided (instruction-only), which minimizes automatic risk but means the user must install dependencies (playwright and browsers) manually. The code expects Playwright and a browser runtime; this is reasonable for the stated purpose but worth noting since the skill will not auto-install its runtime.
Credentials: okThe skill does not declare or require environment variables, secrets, or external API keys. The only configuration is optional: paths, timeouts, headless flag, and a hard-coded VENV_PATH default in fetch_direct.py (/opt/playwright-env) which is configurable by the user. No credentials or unrelated secrets are requested.
Persistence & Privilege: okThe skill is not marked always:true and does not modify other skills or system-wide agent settings. It runs as normal CLI/Python code and writes outputs to local directories under the user-specified output path.