RESIDUAL COMMON CRAWL LEADS — LIVE CONTEXT REVIEW
2026-09-05, fetched 10:28–10:29 UTC. Completed bounded review of five leads from 003-corpus-audit.txt.

RESULT: No verified agent artifact or second actor in these five live pages. Four rare-term hits are explained by product documentation, commercial certification copy, or ordinary proxy/code tutorials. The fifth term is absent from the current page, so its historical context remains unresolved.

METHOD
Seven read-only GETs: five exact lead URLs, HtmlDrag homepage and sitemap. Four workers maximum across different hosts; no creation, account registration, login, admin/edit access, counter endpoint, script execution, or sharing action. Search-engine discovery additionally checked site:htmldrag.com with share/gallery/分享/广场 terms; results were product/documentation pages. No actual share permalink was visited. Raw pages can contain ordinary website tracking identifiers and contact details; this text intentionally includes only reviewed evidence.
Raw fetch metadata: investigation/china/004-residual-fetch.json and 004-htmldrag-fetch.json. Both include UTC, HTTP status, exact URL, body length, SHA256 and raw-file path. Raw bodies reside under pastebins/data/<host>/china-codex-*.html.

1. CILIMIAO — HISTORICAL PHRASE UNRESOLVED; CURRENT PAGE IS DIRECTORY/SEO CONTENT
https://www.cilimiao.cn/
HTTP 200, 1,658,028 bytes.
Title: BT磁力搜索_磁力狗_CILIMAO磁力猫_磁力搜索引擎2025导航大全
Current page is a very large navigation/search directory containing torrent/magnet-search resources, software/tool categories, and extensive general explanatory copy. Neither exact 链接格式测试 nor a distinctive research-agent artifact was located in the current body. Other 测试 occurrences relate to software tests, game testing and download compatibility. No outbound torrent or resource links were followed.
The July Common Crawl score is evidence that the scan matched that exact substring in its corpus, but live content cannot establish its old context. Do not relabel the historical hit definitively false without retrieving its WARC capture. No public anonymous scratch-memory listing established.
Raw: pastebins/data/www.cilimiao.cn/china-codex-residual-20260905.html
SHA256 0094d6eba8f40b0c9f2fd48027b816ad5c19624998172efd7778a95df855d054

2. HTMLDRAG — DOCUMENTED ACCOUNT-BASED SHARING, NO SWARM ARTIFACT OR PUBLIC GALLERY FOUND
https://htmldrag.com/zh/guides
HTTP 200, 151,666 bytes. Guide displays last updated 2026-05-18 01:05; this is a page claim, not an independently anchored creation date.
Exact term 临时测试页面 occurs in section 3.5 AI创造 as one suggested purpose among product introductions, recruitment, course registration, data summaries, sales follow-up and portfolios. It describes what customers could create; it is not itself an anonymous test post.
Guide sections 1 and 4.16 document account creation before use, public share links for Pro users, default seven-day expiry, renewal/revocation controls, and a separate visitor view. This establishes a documented publishing capability but does not prove any anonymous write mechanism or agent use. No content was created to test it.
Raw: pastebins/data/htmldrag.com/china-codex-residual-20260905.html
SHA256 a822b9fba3a5e01178af11da96fb0777d216605c0391b4633442404fb56d7d8f

Read-only listing discovery:
https://htmldrag.com/sitemap.xml returned actual XML, HTTP 200, 954,311 bytes, 539 loc elements. URLs are multilingual product, tool, legal, documentation and blog pages; no path containing /share, /gallery, /archive or /explore. Homepage and guide navigation similarly expose product/blog pages and an account-specific /my-creations link, not a demonstrated public gallery. That private management link was not requested. Sitemap absence is not proof no gallery exists; no public user-work listing or actual share permalink was found in this bounded review.
Sitemap raw: pastebins/data/htmldrag.com/china-codex-sitemap-20260905.html
SHA256 ca1eb8cf51843c87b0c2ca270bb8ce3d75c58ed50965404be9b9cfc44de0c29f
Homepage https://htmldrag.com/zh — HTTP 200, 109,238 bytes.
Raw: pastebins/data/htmldrag.com/china-codex-home-20260905.html
SHA256 4ecc586cbf425508ee3888ac9d26271f81f5b716b4967d76ae727e847a24ed79
Additional primary source supporting unauthenticated viewing of enabled shares: https://htmldrag.com/faq
Conclusion: keep as a low-priority expiring publishing-surface lead, not a NEW_SITES swarm positive. Future useful evidence would be an already-public share URL with dated artifact content; more marketing pages add little.

3. SSOOCC — COMMERCIAL RADIO-CERTIFICATION COPY; SUBSTRING FALSE POSITIVE
https://www.ssoocc.com/64182.html
HTTP 200, 56,162 bytes.
Title concerns TELEC wireless-product certification and a third-party testing agency. Exact 参考链接测试 occurs inside a sentence about Japan MIC Notice No.88 and maintenance of testing specifications. The literal fragment “参考链接测试规范的更新维护也是由mic来进行” joins reference-link wording to testing-specification wording; it does not describe a web-link experiment. Context is Wi-Fi/Bluetooth radio compliance testing.
Displayed date is 2026-09-02, while the inherited score is from the August crawl. This mismatch could reflect a revised/recycled date; no attempt to settle historical publication time. No actor inference rests on the date.
Raw: pastebins/data/www.ssoocc.com/china-codex-residual-20260905.html
SHA256 b0358b1feaa6fadd38cf401fc1dfb9e07950eaad32a7d9ea131d0d5bbc6b9b53

4. 1ITAO — OLD IMAGE-PROXY TUTORIAL
https://www.1itao.com/image-anti-leech.html
HTTP 200, 74,839 bytes.
Title: 图片防盗链解决方案：代理地址缓存图片，加速访问
Displays published 2021-10-10, updated 2025-03-24. Those are page claims, not archive timestamps. cors.zme.ink is one item in a list of image-cache/proxy services alongside WordPress, weserv, Baidu and others. Article explains image hosting/referrer compatibility. No research task, Chinese statistical endpoint, repeated test markers or cross-host artifact join appears in the relevant content. The listed proxy endpoints were not called.
Raw: pastebins/data/www.1itao.com/china-codex-residual-20260905.html
SHA256 27976f861dcef66a64dd5615a6d32b5821887730aae379849571c8b7dec221c0

5. NETNR — NAMED AUTHOR'S DEAD-LINK CHECKER; A REAL CODE-SHARING ECOSYSTEM LEAD
https://www.netnr.eu.org/279
HTTP 200, 22,893 bytes.
Title: dead_link_detection.js. Page attributes author netnr, displays 2019-08-09, and describes checking page links to clean up dead links in navigation pages. Current script defines LinkChecker.PROXY_SERVERS with cors.eu.org, seep.eu.org, codetabs and Netnr link-status services. Thus cors.eu.org is ordinary program configuration, not a proxy-wrapped research data request. The displayed 2019 date may precede later edits to the script; not an immutable code-version date.
The UI exposes Gist/Run/Doc categories and ordinary raw/download links. Discovered read-only URLs include https://www.netnr.eu.org/?c=gist and https://www.netnr.eu.org/279/raw. Neither was enumerated in this bounded review. Login link present. This is a potentially useful code/document-sharing surface for a later dated public-listing survey, with this page itself classified ordinary named-author code. No anonymous publishing capability established.
Raw: pastebins/data/www.netnr.eu.org/china-codex-residual-20260905.html
SHA256 ded42f0361a9184f5c6aed5badcd4b4d24fe8f15111d6d454869dbdc078fefad

NEXT STEPS THAT COULD CHANGE THESE CLASSIFICATIONS
Retrieve cilimiao July WARC context if a residual rare phrase remains worth the cost. For Netnr, a limited read-only public gist inventory could test dates and authorship distribution. For HtmlDrag, search/archive discovery of genuine share URLs is required before any artifact enumeration. None of these five pages supports Chinese-lab attribution; no new positive added to NEW_SITES.md.