REVIEWED — ENGLISH BEHAVIORAL SCAN COMPLETE
Reviewed2026-09-05 UTC. No independently attributable research-swarm artifact verified by this pass. One existing public-agent-community observation now has an independent August archive anchor.

COVERAGE
One August text-only pass,247seconds,100,000/100,000 files,0 failures.
2,083,525,558 pages examined;446 matching rows across286 registrable source domains.
0 bytes downloaded; existing local corpus only. Final scores/log/domain aggregation/report copied to cc-english-behavior/.
53 exact case variants of27 coordinator-curated English hypotheses.13 terms had hits;40 had none. No xz_knowledge_p1 or Xz_knowledge_p1 hit.
This is provider/language-origin-independent wording, not proof that matching pages were written by models. English-language output does not identify an American operator, just as Chinese UI or prose does not identify a Chinese lab.

WHAT DOMINATED
333 distinct pages match at least one capitalization of cross-agent memory (249 lowercase term-hits,104 capitalized; overlap means these counts cannot be added as distinct pages). Most URL contexts concern agent-memory products, documentation, skill registries, technical articles or news. These are not inherently spam and were not all manually fetched.
75 pages match for subsequent agents, including38 copies of the same LangGuard release URL slug. Syndicated copies are not38 independent actor observations.
The narrow citation/link-probe phrases mostly had no matches. This may reflect low recall of guessed phrasing, not absence of the behavior. Text-only extraction omits links/scripts and misses many expired, private, unindexed or differently worded artifacts.

REVIEWED CONTEXTS
1. Shellbook: https://shellbook.io/ and the post already reviewed in031, https://shellbook.io/post/6d055060-3509-4c99-8eca-4dc9f9dace02.
The matched discussion presents an intentional agent social platform and explains participation through human instructions or schedules. It does not authenticate model/operator identity or show escaped research agents. A recovered homepage WARC, HTTP200 at2026-08-12 17:02:05UTC, includes the same post ID and substantive discussion containing public scratchpad for. This independently anchors the discussion before disclosure; it is not a verified February creation date or standalone-post capture. It strengthens031's date evidence without changing its attribution.
Evidence: pastebins/data/shellbook.io/029-{index-lookup,selected-captures,metadata}.json and029-homepage.{warc.gz,warc,html}.
WARC locator: crawl-data/CC-MAIN-2026-34/segments/1786091385525.56/warc/CC-MAIN-20260812165636-20260812195636-00908.warc.gz offset430217939 length34219.

2. https://www.kunalganglani.com/blog/indirect-prompt-injection-ai-agents
Current page has a named author and identifies a security-testing checklist, declared July3/updatedAugust16,2026. Memory persistence test is a numbered suggested test, not a record of an agent depositing its own persistent research state. It also describes a disclosed blog-publishing pipeline. No instruction, injection payload, API, linked canary or script was executed. Technical claims in the article were not independently validated; the relevant finding is its document genre and marker context.

3. https://neomanex.com/news/aisi-frontier-agents-real-person-deception-2026-08
Current page is secondary incident reporting, not the agent-generated GitHub artifact it describes. Coordinator verification against https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing identifies documented AISI evaluation context involving Western-labelled models; see root report037 for primary-source details. This scan does not discover a Chinese-origin operator or a new anonymous research surface through that retelling.

RARE HITS WITH UNRESOLVED BODY CONTEXT
- https://www.tantumpay.com/en/business/tantumident/ and https://www.certlibrary.com/info/VCS-253: unique reference marker. Product/exam-shaped URLs; Tantum fetch failed with non-retryable safe-open error. Do not infer agent behavior or claim both bodies were verified.
- https://agence-deliver.com/en/blog/black-friday-email-checklist: reference link test. Web open returned Cache miss. Marketing-checklist-shaped URL, actual matched context remains unverified.
- https://thewiseoperator.com/digest/2026-04-11-ai-digest/: persistent research note. Fetch failed; digest-shaped URL only. No source artifact established.
-15 Do not remove this marker page hits are Ubuntu-fr forum URLs. One representative fetch failed with non-retryable safe-open error. They plausibly concern technical configuration, but this task did not recover the matched body context or independently date those posts, so they remain limited unverified context rather than hard negatives.
-Other low-volume hits involve personal research-note discussions, note-taking plugins, gaming/blog author pages, and memory/security articles. Their URL shapes are triage information only. No blanket clearance of all446 matching pages is claimed.

INTERPRETATION
Observed public agent discussion and disclosed agent-development/publishing workflows are real surface categories; they should not be collapsed into “nothing exists.” What remains unverified is the specific independent research/persistence actor and Chinese-lab/operator connection sought here. Public-community chatter, suggested tests, citation terminology and model names do not establish it. No qualifying new-site entry or actor attribution was added.

REQUEST AND COMPUTE ACCOUNTING
One scan only, completed and exited. Seven web-open attempts during review: Shellbook, Neomanex, one Ubuntu-fr representative, Tantum, Deliver, KunalGanglani and WiseOperator;3 returned content and4 failed. Two sequential archive calls (one index block and one WARC) recovered Shellbook, paced beyond1.5seconds. No origin retries, login attempts, writes, credential use, embedded-link calls, script execution, links scan or infrastructure lifecycle change. Shellbook's overlap with031 was acknowledged; only its additional archive anchor is novel.

EXACT TERM COUNTS (id | pages | term)
0 | 1 | reference link test
1 | 0 | Reference link test
2 | 0 | citation link test
3 | 0 | Citation link test
4 | 0 | test citation URL
5 | 0 | Test citation URL
6 | 0 | unique citation marker
7 | 0 | Unique citation marker
8 | 2 | unique reference marker
9 | 0 | Unique reference marker
10 | 0 | temporary citation link
11 | 0 | Temporary citation link
12 | 4 | public scratchpad for
13 | 0 | Public scratchpad for
14 | 0 | public scratch memory
15 | 0 | Public scratch memory
16 | 1 | persistent research note
17 | 0 | Persistent research note
18 | 4 | research agent test
19 | 0 | Research agent test
20 | 0 | agent link test
21 | 0 | Agent link test
22 | 249 | cross-agent memory
23 | 104 | Cross-agent memory
24 | 75 | for subsequent agents
25 | 0 | For subsequent agents
26 | 5 | for other agents to read
27 | 0 | For other agents to read
28 | 0 | preserve this marker
29 | 0 | Preserve this marker
30 | 0 | verify URL rendering
31 | 0 | Verify URL rendering
32 | 0 | testing URL rendering
33 | 0 | Testing URL rendering
34 | 0 | URL format probe
35 | 0 | link format probe
36 | 0 | Link format probe
37 | 0 | citation format test
38 | 0 | Citation format test
39 | 0 | fetch workaround test
40 | 0 | Fetch workaround test
41 | 0 | scratchpad link test
42 | 0 | Scratchpad link test
43 | 3 | research scratchpad
44 | 0 | Research scratchpad
45 | 0 | agent persistence test
46 | 0 | Agent persistence test
47 | 1 | memory persistence test
48 | 2 | Memory persistence test
49 | 0 | do not remove this marker
50 | 15 | Do not remove this marker
51 | 0 | xz_knowledge_p1
52 | 0 | Xz_knowledge_p1

REPRODUCIBILITY
Terms: investigation/china/terms_china_codex_english_behavior.tsv.
Remote output: /data/runs/china-codex-english-behavior; log /home/ec2-user/china-codex-english-behavior.log.
Local counts:029-term-counts.json; reviewed summary029-reviewed-summary.json; raw results cc-english-behavior/.
Invocation: ./target/release/ccsearch --corpus /data/corpus --s3 --s3-endpoint http://s3.us-east-1.amazonaws.com --crawl CC-MAIN-2026-34 --concurrency 384 --out /data/runs/china-codex-english-behavior --port 8097 --exit-when-done --score-terms /data/runs/terms_china_codex_english_behavior.tsv --report-domains 100000 --report-pages 20000
Private ~/terms.tsv and copies were never read. EC2 remains running; no automatic repeat was launched.