ObservationOBS-2026-0205v0.1

O5 — In a frozen 60-repository company panel, both high-warning results were on agent instruction files

In a frozen 60-repository company panel, both high-warning results were on agent instruction files.

Research status: STABLE the current conclusions are relatively stable
Evidence level: E2 Controlled experiment
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: 2026-09-21
Created: 2026-09-21
Domain: Privacy
Program: PRG-2026-0201 AI Agent Publication Boundary and Security Closure (APBSC)
Authors: Neo.K (EveMissLab)
AI collaborators: Splice (Claude Code, Anthropic) — Phase II protocols, runners, audits, reports and the integrated edition

Recorded fields

tags: observed (O)
integrated edition appendix A
existence, not prevalence

Source	Relation	Target	Status	ID
`OBS-2026-0205` O5 — In a frozen 60-repository company panel, both high-warning results were on agent instruction files	`supports`	`THY-2026-0203` Agent context as an egress surface	`ACTIVE`	`REL-2026-0522`
`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-2026-0202` Pooled F1–F4: high warnings on every surface — README 3.4%, agent instruction 3.0%, governance 0.9%	`qualifies`	`OBS-2026-0205` O5 — In a frozen 60-repository company panel, both high-warning results were on agent instruction files	`ACTIVE`	`REL-2026-0595`

Canonical URL

Machine-readable

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