TheoryTHY-2026-0205v0.1

Organizational propagation of agent context (hypothesis)

Shared rules, templates, skills and scanners are supply-chain roots: one context error is inherited by every repository that copies it, a widely shared scanner's PASS carries more apparent authority than it earned, and copies of a policy age at different speeds.

Research status: PRELIMINARY a first formalisation or observation exists
Evidence level: E0 Concept only
Data basis: THEORY Theoretical reasoning only; no measurement.
Version: 0.1
Updated: 2026-10-13
Created: 2026-09-21
Domain: Privacy
Program: PRG-2026-0201 AI Agent Publication Boundary and Security Closure (APBSC)
Authors: Neo.K (EveMissLab)
AI collaborators: AI collaboration recorded for the series; the collaborator is not named in the drafts, Splice (Claude Code, Anthropic) — Phase II protocols, runners, audits, reports and the integrated edition

Recorded fields

tags: paper 04

Relations

Source	Relation	Target	Status	ID
`THY-2026-0205` Organizational propagation of agent context (hypothesis)	`contains`	`CLM-2026-0202` H2 — Shared organization context amplifies one disclosure pattern across many repositories	`ACTIVE`	`REL-2026-0513`
`RES-2026-0201` Why passing checks does not close the publication boundary	`develops`	`THY-2026-0205` Organizational propagation of agent context (hypothesis)	`ACTIVE`	`REL-2026-0508`
`PAP-2026-0205` Paper 04 — Organizational agent context propagation	`formalizes`	`THY-2026-0205` Organizational propagation of agent context (hypothesis)	`ACTIVE`	`REL-2026-0535`

History and provenance

Canonical URL

https://evemisslab.com/ai/theory/THY-2026-0205/

Machine-readable

/ai/theory/THY-2026-0205/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