zhuque-detect — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited zhuque-detect (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
把一段中文文本喂给腾讯朱雀(matrix.tencent.com/ai-detect),拿到 AI 生成检测结果,并导出与产品「下载报告」一致的官方检测报告单 PDF(含环形图、AI 分布图、片段解析表、逐段 AIGC 值与原文)。
scripts/ 下装一次依赖:npm install(只装 playwright-core,不下载浏览器)。 # macOS
open -a "Google Chrome" --args --remote-debugging-port=9222
# Linux
google-chrome --remote-debugging-port=9222
# Windows
chrome.exe --remote-debugging-port=9222该 Chrome 需能正常打开 matrix.tencent.com/ai-detect 并手动跑通检测(朱雀匿名即可用,有每日免费额度)。
cd scripts
npm install # 一次
node run.mjs # 默认 sample.txt → reports/朱雀报告单-<时间>.pdf
node run.mjs ./my.txt ./out.pdf # 自定义输入文本 / 输出路径调试端口非 9222 时用 ZHUQUE_CDP=http://127.0.0.1:PORT node run.mjs。
fp/ARGUS_XSS_V3 令牌。空白自动化 chromium 无有效令牌 → Invalid request。连你已登录的真机即天然带齐令牌,故脚本用 connectOverCDP 接管真机、新开标签页跑。contentWindow.print()(原生打印框,脚本点不动、还冻结页面)。脚本劫持该 iframe 的 print,截获其报告单 HTML,注入 <base> 后用 CDP Page.printToPDF 渲染成等价 PDF —— 全程不弹原生框。详见 reference/anti-bot-notes.md。
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.