Audit P2 H. DPIA-agenten navngav Schrems II-risikoen (risiko 7) men kunne ikke vurdere den
— ingen sti til TIA-metodikk. Nå nåbar, og ny verifisert metodikk forfattet i KB.
- data-residency-audit-monitoring.md: Schrems II-stubb (3 punkter) utvidet til full EDPB
seks-stegs-TIA (Recommendations 01/2020) + CLOUD Act/FISA 702/EO 12333-restanalyse
+ EO 14086/DPF-nåstatus + tekniske tilleggstiltak (CMK/Customer Lockbox/Confidential
Computing). Korrigerer feilantakelsen «EUDB eliminerer alle overføringer». Last updated 2026-05→06.
- dpia-agent.md: betinget cross-border-ruting + obligatorisk TIA-prosedyre under risiko 7
(operasjonaliserer DPO-svaret «kan amerikanske myndigheter nå disse dataene?»)
- dpia.md: betinget KB i delegeringsprompt; CLAUDE.md: dpia-agent rutingsindeks oppdatert
Verifisert 2026-06-18 (WebSearch, juridiske primærkilder):
- EDPB Recommendations 01/2020 seks-stegs-metodikk + tiltaks-rangering (tekniske sterkest)
- DPF gyldig gjeldende rett; Latombe avvist av Underretten 2025-09-03 (T-553/23),
anket 2025-10-31 → C-703/25 P (ingen berammet dato per mai 2026)
- FISA §702: statutt-utløp 2026-04-20 + 45-dagers extension, reautorisasjon under forhandling
juni 2026; innsamlingsautoritet består via FISA-domstols-sertifiseringer (mars 2026) til mars 2027
- CLOUD Act uendret av DPF; EUDB fjerner ikke tredjelands tilgangsmulighet
validate-plugin: 223 PASS
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01REiKFhP4w6xGXXqWKpPCJJ
Release-gaten før v1.16.0: bekreftet eksakt engelsk tittel-ordlyd for ASI01–ASI10
mot OWASP GenAI Security Projects offisielle publisering på genai.owasp.org
(9. desember 2025), hentet direkte to ganger uavhengig. Sekundærkilde-spriket som
ros-ai-threat-library.md:541 advarte mot er nå løst mot primærkilden.
Fire titler var feil (KB fulgte aggregator-varianter, ikke offisiell tekst):
- ASI02: «Tool Misuse & Exploitation» → «Tool Misuse»
- ASI03: «Agent Identity & Privilege Abuse» → «Identity & Privilege Abuse»
- ASI04: «Agentic Supply Chain Compromise» → «Agentic Supply Chain Vulnerabilities»
- ASI08: «Cascading Agent Failures» → «Cascading Failures»
Rettet i alle 6 forekomster (hovedtabell + inline OWASP Agentic-mappingrader 579/597).
Kildemerknad (:541) oppdatert: hedge om uverifisert ordlyd erstattet med eksplisitt
primærkilde-referanse + hvilke sekundærvarianter som florerer.
Notasjon (:2026): uendret. Offisiell blogg bruker ASIxx uten årstall, men KB bruker
konsekvent :ÅRSTALL for OWASP-IDer (jf. LLM05:2025) — intern konsistens beholdt,
flagget separat for normaliserings-beslutning.
Verifisert: validate-plugin.sh 219 PASS.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Pre-trekexecute snapshot of in-progress CLAUDE.md/SKILL.md edits and
extracted docs/ files. Captured as one commit so /trekexecute claude-design
can run against a clean working tree.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Phase 2 bulk replace produced a few factually wrong attributions where
real publicly known sector documents/datasets/personas were incorrectly
re-attributed to the fictional generic entity. Genericize those
references instead.
- ros-sector-checklists.md: V440 håndbok citation -> "sektorvise
faglige håndbøker"; tilsynsmyndighet list -> generic phrasing
- master-data-management-ai.md: NVDB row -> generic "sektor-/fagregistre"
- ai-center-of-excellence-setup.md: NVDB integration line -> generic
"sektorvise nasjonale registre"
- multimodal-prompt-engineering.md: system_message persona -> generic
"fagingeniør i norsk offentleg sektor"
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Additional factual updates from batch 3 research:
- responsible-ai-training-awareness.md: module renamed
"Azure AI Studio" → "Microsoft Foundry" (3 occurrences)
- transparency-documentation-standards.md: ISO/IEC 42001 scope expanded
to include Copilot Studio, Microsoft Foundry, Security Copilot,
GitHub Copilot, Dragon Copilot
- ai-act-compliance-guide.md: same ISO 42001 scope expansion
- human-in-the-loop-oversight.md: AI approval stages in Copilot Studio
(GPT-o3 as AI approver, new Human in the loop connector)
- continuous-improvement-feedback-loops.md: MLflow 3 Feedback vs
Expectation assessment types, Genie Code trace analysis
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Add /ultraresearch-local for structured research combining local codebase
analysis with external knowledge via parallel agent swarms. Produces research
briefs with triangulation, confidence ratings, and source quality assessment.
New command: /ultraresearch-local with modes --quick, --local, --external, --fg.
New agents: research-orchestrator (opus), docs-researcher, community-researcher,
security-researcher, contrarian-researcher, gemini-bridge (all sonnet).
New template: research-brief-template.md.
Integration: --research flag in /ultraplan-local accepts pre-built research
briefs (up to 3), enriches the interview and exploration phases. Planning
orchestrator cross-references brief findings during synthesis.
Design principle: Context Engineering — right information to right agent at
right time. Research briefs are structured artifacts in the pipeline:
ultraresearch → brief → ultraplan --research → plan → ultraexecute.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
