The MRIS Project

Established standards. One threat model. Concrete hardening.

Targeted ISMS hardening against Frontier AI attacks. MRIS assesses which security controls still work against autonomously operating AI attackers – and which only work on paper.

MRIS assesses established security standards control by control against GenAI-accelerated attacks – currently ISO/IEC 27001 (Annex A) and TISAX® 2027 –, points to concrete Mythos-Hardening Controls (MHC) from a cross-standard catalog and operationalises them with MRIS.bd.1 as a user-defined module for BSI IT-Grundschutz.

Free · CC BY-NC 4.0 · No registration · For CISOs and security leaders

Why “Mythos”?

Mythos (Anthropic) was the first frontier AI model whose capabilities in an attacker’s hands fundamentally changed the security landscape. MRIS uses it as the reference threat model: every control is measured against an attacker with Mythos-level capabilities. In public discourse, systems of this capability class are called Frontier AI or agentic AI – within MRIS, "Mythos" is the vendor-neutral name for exactly this class.

1
AssessEvery control of a standard, individually, against the threat model
2
ClassifyFour categories – from robust to pure friction
3
HardenMatching MHC from the catalog close the gaps
The MHC Catalog

One catalog. Applied per standard.

Implement once, benefit repeatedly: each MHC is defined across standards – the same measure closes gaps in every framework that references it and yields audit evidence for several assessments at once. Instead of maintaining a separate catalog per framework, you prioritize one central catalog by breadth of impact. It grows with every standard assessed.

MHCISO 27001TISAX® 2027IT-Grundschutz
MHC-01Post-Quantum Strategy and Cryptographic Inventory

Protects long-lived confidential data captured today from later decryption (“harvest now, decrypt later”) and, with the cryptographic inventory, lays the groundwork for an orderly migration to post-quantum algorithms.

ISO/IEC 27001 · Annex AA.8.24
Open in the finder →
TISAX® 2027 · ISAnot assigned
IT-Grundschutz · MRIS.bd.1Requirement A6: Crypto inventory & PQC
View the module →

Breadth of impact: 1 ISO controls · 1 IT-GS requirement

MHC-02SBOM and Build Provenance

Makes the origin and components of every piece of software verifiable – the basis for detecting AI-accelerated supply-chain attacks and tampered builds before they reach production.

ISO/IEC 27001 · Annex AA.5.19–A.5.22, A.8.4, A.8.30
Open in the finder →
TISAX® 2027 · ISAnot assigned
IT-Grundschutz · MRIS.bd.1Requirement A8: SBOM & provenance
View the module →

Breadth of impact: 6 ISO controls · 1 IT-GS requirement

MHC-03Phishing-Resistant MFA

Renders intercepted or real-time-relayed credentials worthless, removing the basis for automated, AI-scaled phishing.

ISO/IEC 27001 · Annex AA.5.17, A.6.7, A.8.1, A.8.5, A.8.23
Open in the finder →
TISAX® 2027 · ISA4.1.1, 4.1.2, 4.1.3, 5.1.2, 5.2.7, 6.1.3
Open in the finder →
IT-Grundschutz · MRIS.bd.1Requirement A2: Phishing-resistant MFA
View the module →

Breadth of impact: 5 ISO controls · 10 TISAX® findings · 1 IT-GS requirement

MHC-04Workload Identity and Zero Trust

Ties access to verified workload identities instead of network zones – reducing lateral movement once an AI attacker has initial access, and enabling the safe use of AI agents.

ISO/IEC 27001 · Annex AA.5.15, A.5.16, A.6.7, A.8.2, A.8.20–A.8.22
Open in the finder →
TISAX® 2027 · ISAnot assigned
IT-Grundschutz · MRIS.bd.1Requirement A5: Workload identities
View the module →

Breadth of impact: 7 ISO controls · 1 IT-GS requirement

MHC-05Behavior-Based Detection

Detects unknown, signature-less malware by its behavior as well as attacks deliberately split into many small, individually inconspicuous steps – in their sum rather than step by step.

ISO/IEC 27001 · Annex AA.5.3, A.5.7, A.5.14, A.5.15, A.8.1, A.8.3, A.8.4, A.8.7, A.8.12, A.8.15, A.8.16
Open in the finder →
TISAX® 2027 · ISA1.6.1, 1.6.3, 5.2.3, 5.2.4, 5.2.7
Open in the finder →
IT-Grundschutz · MRIS.bd.1Requirement A4: Behaviour-based detection
View the module →

Breadth of impact: 11 ISO controls · 9 TISAX® findings · 1 IT-GS requirement

MHC-06Containers and Confidential Computing

Hardens runtime environments through signed images and attestation – a compromised artifact does not reach production unnoticed, and data stays protected even during processing.

ISO/IEC 27001 · Annex AA.5.23, A.8.31
Open in the finder →
TISAX® 2027 · ISAnot assigned
IT-Grundschutz · MRIS.bd.1Requirement A12: Signed containers
View the module →

Breadth of impact: 2 ISO controls · 1 IT-GS requirement

MHC-07Multi-Tenancy Isolation

Enforces demonstrable separation between tenants – a compromised tenant does not become a springboard to others; effectiveness is proven by separation tests, not merely asserted.

ISO/IEC 27001 · Annex AA.5.23, A.8.22
Open in the finder →
TISAX® 2027 · ISAnot assigned
IT-Grundschutz · MRIS.bd.1Requirement A13: Tenant separation
View the module →

Breadth of impact: 2 ISO controls · 1 IT-GS requirement

MHC-08Immutable Backups

Ensures backups remain restorable even with compromised admin rights, and that recovery actually works in an emergency instead of existing only on paper.

ISO/IEC 27001 · Annex AA.5.29, A.5.30, A.5.33, A.8.13, A.8.14
Open in the finder →
TISAX® 2027 · ISA5.2.8
Open in the finder →
IT-Grundschutz · MRIS.bd.1Requirement A3: Immutable backups
View the module →

Breadth of impact: 5 ISO controls · 3 TISAX® findings · 1 IT-GS requirement

MHC-09AI-Assisted Security Testing

Shortens the time between a known vulnerability and its remediation to a pace that keeps up with AI-accelerated exploit development.

ISO/IEC 27001 · Annex AA.8.8, A.8.25, A.8.26, A.8.28, A.8.29, A.8.32
Open in the finder →
TISAX® 2027 · ISA1.3.4, 5.2.5, 5.2.6
Open in the finder →
IT-Grundschutz · MRIS.bd.1Requirement A9: Pipeline security testing
View the module →

Breadth of impact: 6 ISO controls · 6 TISAX® findings · 1 IT-GS requirement

MHC-10Continuous Control Monitoring

Closes the window between two periodic review cycles in which new attack patterns, incidents or system changes would otherwise remain undetected until the next round.

ISO/IEC 27001 · Annex AA.5.18, A.5.35, A.5.36, A.8.9
Open in the finder →
TISAX® 2027 · ISA1.1.1, 1.2.1, 1.3.1, 1.3.3, 1.3.4, 1.5.1, 1.6.3, 4.1.3, 4.2.1, 5.2.9, 6.1.2, 6.1.3
Open in the finder →
IT-Grundschutz · MRIS.bd.1Requirement A11: Continuous verification
View the module →

Breadth of impact: 4 ISO controls · 18 TISAX® findings · 1 IT-GS requirement

MHC-11SOAR and Tier-1 Automation

Shortens the response time to a security-relevant event to a level that no longer depends on human processing speed alone.

ISO/IEC 27001 · Annex AA.5.5, A.5.24–A.5.26
Open in the finder →
TISAX® 2027 · ISA1.6.2
Open in the finder →
IT-Grundschutz · MRIS.bd.1Requirement A10: Automated response
View the module →

Breadth of impact: 4 ISO controls · 4 TISAX® findings · 1 IT-GS requirement

MHC-12Threat-Led Penetration Testing

Validates the entire defense chain against realistic, AI-driven attack scenarios – revealing whether detection and response work in practice rather than only on paper.

ISO/IEC 27001 · Annex AA.5.35, A.8.29
Open in the finder →
TISAX® 2027 · ISAnot assigned
IT-Grundschutz · MRIS.bd.1Requirement A14: TLPT with AI scenarios
View the module →

Breadth of impact: 2 ISO controls · 1 IT-GS requirement

MHC-13AI Agent Governance

Prevents an AI-powered assistant from independently pulling in an unvetted external tool, service or software package while working on a task, and additionally constrains the identity, prompt-injection exposure and response time of agents in production.

ISO/IEC 27001 · Annex AA.5.9, A.5.16, A.8.27
Open in the finder →
TISAX® 2027 · ISA1.3.3, 1.3.4
Open in the finder →
IT-Grundschutz · MRIS.bd.1Requirement A7: Regulated AI agents
View the module →

Breadth of impact: 3 ISO controls · 4 TISAX® findings · 1 IT-GS requirement

MHC-14Independent Verification of Supplier Evidence

Prevents an AI-assisted, convincingly forged or embellished supplier attestation from being accepted as sufficient without detection.

ISO/IEC 27001 · Annex Anot assigned
TISAX® 2027 · ISA6.1.1, 6.1.3
Open in the finder →
IT-Grundschutz · MRIS.bd.1not assigned

Breadth of impact: 5 TISAX® findings

MHC-15AI-Resistant Identity Verification for Staff/Access

Prevents a convincing deepfake identity or forged document from being accepted undetected in hiring or facility-access processes.

ISO/IEC 27001 · Annex Anot assigned
TISAX® 2027 · ISA2.1.1, 2.1.3, 3.1.1
Open in the finder →
IT-Grundschutz · MRIS.bd.1not assigned

Breadth of impact: 6 TISAX® findings

MHC-16Multi-Agent Integrity *

Limits how far a manipulated, faulty or compromised agent can act within a chain or orchestration of multiple AI agents before damage occurs or spreads.

ISO/IEC 27001 · Annex Anot assigned
TISAX® 2027 · ISAOriginal addition without a TISAX® finding – see the Implementation Guide (Part II).
IT-Grundschutz · MRIS.bd.1not assigned

Breadth of impact: TISAX®: original

Catalog status: 16 MHC · August 2026. * MHC-16 is an original addition beyond the TISAX® diagnosis. Seven MHC (highlighted) apply across all three frameworks; MHC-01 to MHC-13 are additionally operationalised as IT-Grundschutz requirements (MRIS.bd.1) – one implementation, effect across up to three frameworks.

The Standards

Three standards. Two assessments. One operationalisation.

Downloads

All publications. Free. CC BY-NC 4.0.

ISO/IEC 27001 · Annex A

MRIS for ISO/IEC 27001

Analysis – MRIS v1.8PDF · July 2026 · CC BY-NC 4.0
Implementation Guide v1.4PDF · July 2026 · CC BY-NC 4.0
Machine-readable edition – YAMLYAML · v1.8 · July 2026 · CC BY-NC 4.0
TISAX® ISA 2027 · Information Security

MRIS for TISAX® 2027

Analysis – Part IPDF · July 2026 · CC BY-NC 4.0
Implementation Guide v1.1PDF · July 2026 · CC BY-NC 4.0
BSI IT-Grundschutz · user-defined

MRIS.bd.1 – Mythos-Resistant Hardening of the ISMS

⚠ Not reviewed, approved or certified by the BSI.
ModulePDF · v1.2 · August 2026 · CC BY-NC 4.0
Implementation GuidancePDF · v1.2 · August 2026 · CC BY-NC 4.0
Machine-readable editionYAML · v1.2 · August 2026 · CC BY-NC 4.0
Cross-Reference TableXLSX · v1.2 · August 2026 · CC BY-NC 4.0

License: CC BY-NC 4.0 · © 2026 Richard Peddi · No registration required.

Usage note

The MRIS publications are working aids for assessing the effectiveness of existing security controls. They assume an established ISMS and do not replace it. They do not constitute legal, compliance or certification advice, make no claim to completeness and establish no warranty. Use is at your own responsibility.

TISAX® independence notice

TISAX® is a registered trademark of the ENX Association; the ENX Association administers TISAX® on behalf of the German Association of the Automotive Industry (VDA), which develops and publishes the underlying requirements catalog (VDA ISA). MRIS is an independent, privately produced work with no affiliation to the ENX Association or the VDA. It is neither part of the official TISAX® assessment process nor authorized, reviewed or endorsed by ENX, and does not replace a TISAX® maturity assessment by an accredited audit provider.