ReferenceDemonstrated real incidentv1.22.1

In plain English

This page is reference material: definitions, schemas, catalogs, templates, and implementation records.

  • Why this matters: AI risk can come from the whole arrangement, not one obvious model.
  • What to look for: data, memory, routes, adapters, tools, evaluators, updates, and rollback paths.
  • Technical version below: the expert terminology remains available and is linked through the glossary.

Report Use and Evidence Boundaries

Evidence levelDemonstrated real incidentTechnical label: Demonstrated

The expanded package preserves raw uploaded reports and public-safe summaries. It also records their use in .uai memory.

Boundary rules

  1. Raw reports are preserved for project continuity.
  2. Public pages use sanitized, non-operational summaries.
  3. Source reports are not treated as independent consensus.
  4. Speculative language remains labeled as speculative.
  5. Incident claims are not upgraded without primary-source review.
  6. No exploit steps, replication recipes, or backdoor-construction instructions are added to public pages.

Where to inspect