ResultRST-2026-0201v0.1

Company panel: both high warnings on agent instruction files (2/40), none on README (0/59) or governance (0/51)

In the frozen 60-repository company panel, the only high-warning cells were two L3 cells on AI-native companies' agent instruction files; the same repositories were L0 or L1 on README and governance files.

Research status: STABLE the current conclusions are relatively stable
Evidence level: E2 Controlled experiment
Result: MIXED
Data basis: BLIND PUBLIC DATA Real public files measured by an algorithm inside a sealed process. No person and no AI model read them; only coded features left the process. The numbers may be distorted.
Version: 0.1
Updated: 2026-10-13
Created: 2026-09-22
Domain: Privacy
Program: PRG-2026-0201 AI Agent Publication Boundary and Security Closure (APBSC)
Authors: Neo.K (EveMissLab)
AI collaborators: ChatGPT (OpenAI) — RBPM v0.8.3 instrument and its Phase I evidence packages

Observed result

metrics

by_surface

GENERAL_README

high_warning: 0
analyzable: 59

AI_INSTRUCTION_SELECTED

high_warning: 2
analyzable: 40

GOVERNANCE_FAMILY

high_warning: 0
analyzable: 51

Interpretation

interpretation: Existence on companies' agent files; concentration on that surface was later tested on a balanced fresh panel and did not recur.

Limitations

limitations: Exploratory, non-probability frame; not a prevalence estimate.
No human checked any finding; secret-like means a shape and was never tested.
Current public state only, observed once.

Claims

Source	Relation	Target	Status	ID
`RST-2026-0201` Company panel: both high warnings on agent instruction files (2/40), none on README (0/59) or governance (0/51)	`supports`	`OBS-2026-0205` O5 — In a frozen 60-repository company panel, both high-warning results were on agent instruction files	`ACTIVE`	`REL-2026-0576`
`RST-2026-0201` Company panel: both high warnings on agent instruction files (2/40), none on README (0/59) or governance (0/51)	`supports`	`OBS-2026-0203` O3 — Public AI collaboration files can contain concrete workstation, runtime, session and internal-network context	`ACTIVE`	`REL-2026-0577`

Relations

Source	Relation	Target	Status	ID
`RST-2026-0201` Company panel: both high warnings on agent instruction files (2/40), none on README (0/59) or governance (0/51)	`supports`	`OBS-2026-0205` O5 — In a frozen 60-repository company panel, both high-warning results were on agent instruction files	`ACTIVE`	`REL-2026-0576`
`RST-2026-0201` Company panel: both high warnings on agent instruction files (2/40), none on README (0/59) or governance (0/51)	`supports`	`OBS-2026-0203` O3 — Public AI collaboration files can contain concrete workstation, runtime, session and internal-network context	`ACTIVE`	`REL-2026-0577`
`EXP-2026-0201` Phase I company and bridge measurements (2026-09-20 to 2026-09-22)	`produces`	`RST-2026-0201` Company panel: both high warnings on agent instruction files (2/40), none on README (0/59) or governance (0/51)	`ACTIVE`	`REL-2026-0575`

History and provenance

Canonical URL

https://evemisslab.com/ai/results/RST-2026-0201/

Machine-readable

/ai/results/RST-2026-0201/index.json

Snapshot

AI-SNAPSHOT-v0.1-58e716495670

Provenance

source: EveMissLab research collection: AI Agent Publication Boundary and Security Closure (真本體論14)
extracted_by: Splice (Claude Code), reading the open-source release's own manifests, locks and pooled outputs, and the hashes of the internal drafts
extracted_at: 2026-10-13
generator: tools/extract_all.py
claim_boundary: status, evidence level and result type follow the source artifact's own stated claim boundary; nothing is upgraded beyond what the report supports