·
Research Report · v1.0

AI Security Threat Landscape
& Coverage Benchmark 2026

Six domains. Eight industries. Five maturity levels. The baseline every enterprise AI security programme needs — built on MITRE ATLAS, OWASP GenAI, and NIST AI RMF.

Inaugural Edition
June 2026
1.0 — Analyst Baseline
MITRE ATLAS · OWASP GenAI · NIST AI RMF
Q4 2026 (Proprietary Data)
41/100
Enterprise readiness for
AI agent security — the
largest coverage gap identified
39/100
Enterprise readiness for
AI supply chain security —
the most underestimated risk
72/100
Technology sector coverage
score — highest of all
industries assessed
46/100
Average cross-industry
MITRE ATLAS coverage —
most organisations uncovered
against 54% of techniques
Executive Summary

The State of Enterprise AI Security in 2026

Artificial intelligence has moved from experimental infrastructure to business-critical infrastructure in less than three years. Organisations are deploying enterprise copilots, RAG systems, AI coding assistants, autonomous agents, and agentic workflows at a pace that their security programmes have not kept up with.

The threat landscape has evolved equally fast. Prompt injection, agent abuse, retrieval poisoning, excessive agency, model theft, and AI supply-chain attacks are now recognised as major enterprise risks by OWASP, MITRE, NIST, and the Cloud Security Alliance. The OWASP GenAI Security Project — now a flagship OWASP initiative — continues to expand its documentation of critical risks affecting LLMs, GenAI systems, and emerging agentic AI platforms.

"Most enterprises are defending the AI they had in 2023. They are deploying the AI of 2026. The gap between those two realities is where the most significant security risk now lives."

AIZA-HexTyx Research, 2026

This inaugural AIZA-HexTyx benchmark establishes a structured coverage baseline across six threat domains and eight industry sectors. It draws on six authoritative sources — MITRE ATLAS, OWASP GenAI, OWASP Top 10 for LLM Applications, NIST AI RMF, enterprise incident disclosures, and public AI security research — to produce coverage estimates that practitioners, CISOs, and boards can use as a reference point for their own programmes.

The methodology is transparent and reproducible. Coverage scores are structured analyst estimates derived from framework analysis, not survey data — a baseline that becomes more precise as proprietary tool data accumulates through the AIZA-HexTyx free assessment platform in the quarters ahead.

Key finding: The two lowest-coverage domains — AI agent security (41/100) and AI supply chain security (39/100) — are also the two fastest-growing adoption categories. Organisations are deploying autonomous agents and third-party AI components faster than they are securing them.

Methodology

How This Benchmark Was Built

The AIZA-HexTyx Coverage Benchmark uses a six-domain threat model derived from the intersection of four major AI security frameworks. Coverage scores represent the proportion of domain-relevant MITRE ATLAS techniques and OWASP controls that a typical organisation at each industry tier is assessed to have addressed, based on publicly available framework documentation, enterprise deployment patterns, and disclosed security incidents.

Baseline Methodology Note

This v1.0 report is a structured analyst baseline — not a survey. Coverage scores are derived from cross-referencing framework requirements against typical enterprise deployment patterns documented in public research. This is the same approach used by leading analyst firms when proprietary data is not yet available.

The Q4 2026 edition will incorporate real usage data from the AIZA-HexTyx free tool platform: the MITRE ATLAS Coverage Calculator™, MITRE Security Mapping Tool™, MITRE Coverage Benchmark™, and Agent Security Assessments. That data will transform this from an analyst baseline into a proprietary benchmark with statistically grounded scores.

S1
MITRE ATLAS (Adversarial Threat Landscape for AI Systems)The primary threat framework. Used for attack technique categorisation, adversary behaviour mapping, and coverage calculation. ATLAS provides the foundational taxonomy against which all coverage scores are measured.
S2
OWASP GenAI Security ProjectFlagship OWASP initiative documenting critical security risks for LLMs, GenAI systems, and agentic AI platforms. Used for vulnerability taxonomy and enterprise readiness assessment, particularly for agent security and RAG risk categories.
S3
OWASP Top 10 for LLM ApplicationsApplication security baseline providing vulnerability prioritisation and control assessment criteria. Used for prompt injection coverage assessment and enterprise readiness scoring across LLM-facing controls.
S4
NIST AI Risk Management Framework (AI RMF)US federal AI risk governance framework providing the Govern-Map-Measure-Manage structure. Used for governance maturity assessment and the five-level maturity model in Section 5.
S5
Enterprise AI Security Incident Reports & DisclosuresPublic incident reports, regulatory filings, and security researcher disclosures. Used to validate real-world attack trends, identify governance gaps, and calibrate coverage scores against observed failure patterns.
S6
Cloud Security Alliance & Public AI Security ResearchCSA research on AI security, plus peer-reviewed and practitioner research on emerging attack trends, agent security analysis, and AI supply chain risk. Used for maturity validation and 2027 forecast calibration.
Section 2 — Threat Landscape

The Six AI Threat Domains

The HexTyx Coverage Model organises the AI threat landscape into six primary domains. Each domain maps to specific MITRE ATLAS tactics and OWASP categories. The enterprise readiness score represents our assessment of the proportion of relevant controls that a typical enterprise currently has in place — not the maximum possible coverage, but where most organisations actually are in 2026.

Domain 01 · MITRE ATLAS: AML.T0051, T0054
Prompt & Instruction Attacks
Critical

The foundational LLM vulnerability. AI models cannot inherently distinguish trusted instructions from adversarial inputs — making prompt injection the entry point for a majority of AI attack chains. Direct injection targets chatbots and copilots directly; indirect injection embeds malicious instructions in retrieved content, emails, and documents that AI systems process autonomously.

Why coverage is higher than other domains: Prompt injection is the most documented AI risk and has the most mature tooling. Most enterprises have deployed some combination of input filtering, system prompt hardening, and output validation — though sophisticated attacks regularly bypass these controls.

Key OWASP mapping: LLM01:2025 Prompt Injection, LLM02:2025 Sensitive Information Disclosure.

Enterprise Readiness
62 / 100
Domain 02 · MITRE ATLAS: AML.T0080, T0082, T0090
Agent Abuse & Excessive Agency
Critical

The fastest-growing AI security gap. Autonomous AI agents can access systems, call APIs, execute workflows, store memory, and take actions that have real business consequences. The OWASP Agentic Security Initiative identifies goal hijacking, tool misuse, and cascading failures as primary concern areas. Unlike prompt injection — where the impact is a response — agent abuse enables actions.

Why coverage is the lowest of all domains: Most enterprise security programmes were designed before autonomous agents became mainstream. Tool permission governance, MCP security validation, agent memory controls, and workflow security testing are not yet standard practice. Most organisations deploying agents are doing so without systematic security review.

Key OWASP mapping: LLM06:2025 Excessive Agency, LLM07:2025 System Prompt Leakage.

Enterprise Readiness
41 / 100
Domain 03 · MITRE ATLAS: AML.T0020, T0086
RAG & Retrieval Attacks
High

Enterprise AI increasingly relies on Retrieval-Augmented Generation — AI systems that retrieve information from internal knowledge bases before responding. This creates a new attack layer: corrupting what gets retrieved. Retrieval poisoning, context poisoning, unauthorised retrieval, and cross-tenant leakage are all active threat categories that sit below the model layer and above the data layer — a gap that traditional security controls on either side don't adequately address.

Why coverage is low: Data access controls govern who can read files. They don't automatically govern which chunks get retrieved from a vector store. RAG-specific controls — chunk-level access control, retrieval scope validation, knowledge base isolation — are not yet standard in enterprise security programmes.

Key OWASP mapping: LLM08:2025 Vector and Embedding Weaknesses, LLM02:2025 Data Leakage.

Enterprise Readiness
46 / 100
Domain 04 · MITRE ATLAS: AML.T0057, T0060
Data Security & Leakage
Critical

AI systems extract information from context windows, retrieved documents, and fine-tuning data and reproduce it in outputs — often in ways that bypass traditional DLP controls because the exfiltration is semantically generated text, not file transfer or network egress. Prompt leakage, training data memorisation, cross-tenant data disclosure, and sensitive document exposure through RAG are all active risk categories with documented real-world incidents.

Why coverage is higher than agents and supply chain: Enterprises have mature data classification and DLP programmes that partially address this domain. The gap is in AI-specific controls: output monitoring for semantic data disclosure, AI-specific DLP rules, and prompt log analysis.

Key OWASP mapping: LLM02:2025 Sensitive Information Disclosure, LLM06 cross-system data exposure.

Enterprise Readiness
57 / 100
Domain 05 · MITRE ATLAS: AML.T0006, T0010, T0110
Model & Supply Chain Security
High

Few organisations build their own foundation models. Most deploy AI through a supply chain of third-party models, APIs, plugins, MCP servers, open-source frameworks, and fine-tuned derivatives. Each dependency is a potential attack vector. Model theft — extracting proprietary capability through repeated querying — is a growing concern. Dependency poisoning, plugin compromise, and vendor security failures are increasingly treated by CISOs as supply chain risk analogous to software dependency attacks.

Why this is the most underestimated risk: AI supply chain security doesn't yet have a mature vendor risk management framework equivalent. Most procurement processes evaluate AI vendors on performance metrics, data handling terms, and SLAs — not model security, inference-time attack resilience, or update change management.

Key OWASP mapping: LLM09:2025 Misinformation, LLM05:2025 Improper Output Handling, supply chain vectors from OWASP AI Exchange.

Enterprise Readiness
39 / 100
Domain 06 · NIST AI RMF: GOVERN, MAP, MEASURE
Governance & Compliance Failures
Critical

Not every AI security incident starts with a technical exploit. A significant proportion originates from governance failures: AI systems deployed without security review, agents operating without defined scope, no inventory of AI systems, no incident response procedures, unreviewed third-party AI vendors, and regulatory obligations not yet mapped to AI-specific controls. AI adoption is outpacing governance maturity across all industry sectors.

Why governance scores moderate despite critical rating: Most enterprises have general governance processes — risk management, compliance frameworks, vendor assessment — that partially translate to AI. The gap is in AI-specific governance: dedicated AI inventory, AI risk classification, AI-specific incident response, and agent-level permission governance.

Key framework mapping: NIST AI RMF GOVERN 1.1–6.2, EU AI Act Article 9 (risk management system), ISO/IEC 42001.

Enterprise Readiness
52 / 100
Section 3 — Coverage Model

The HexTyx AI Security Coverage Model

Coverage scores are calculated using a weighted model that reflects the current risk profile of enterprise AI deployments. Agent and governance domains carry the highest weights because they represent the largest coverage gaps and the fastest-growing risk categories. Prompt security carries a lower weight than its public prominence might suggest — it is the most mature category and most enterprises have at least basic controls in place.

Agent Security20%
️ Governance & Compliance20%
Prompt Security15%
️ RAG Security15%
Data Protection15%
Supply Chain15%

Applying the weighted model to the domain scores above produces a cross-industry weighted average of approximately 48/100 — consistent with the interpretation that most enterprises are covered against roughly half the MITRE ATLAS techniques relevant to their AI deployments, with significant variance by sector, company size, and AI maturity level.

Interpretation: A score of 48/100 does not mean 52% of attacks will succeed. It means organisations have not addressed the controls that would mitigate 52% of relevant MITRE ATLAS techniques. Some of those unaddressed techniques may never be exploited. Others are actively being used by adversaries today — particularly in the agent abuse and supply chain categories.

Section 4 — Industry Benchmark

AI Security Coverage by Industry Sector

Industry coverage scores reflect the intersection of existing security maturity (which varies significantly by sector), AI adoption pace (faster in technology and financial services than in legal and manufacturing), and regulatory pressure (highest in healthcare and financial services). Technology companies score highest primarily because of existing DevSecOps culture and security testing investment — not because of AI-specific controls.

Industry Coverage Score Maturity Tier Primary Strengths Primary Gaps
Technology & SaaS
72
Managed →
Optimized
Security testing, DevSecOps, monitoring Agent supply chain, MCP security
Financial Services
64
Managed Governance, IAM, compliance processes Agent security, runtime monitoring
️ Government
61
Managed FedRAMP controls, formal security frameworks AI-specific testing, agent governance
Healthcare
54
Developing →
Managed
Access controls, HIPAA compliance processes Prompt injection testing, RAG access controls
️ Legal & Professional
52
Developing →
Managed
Data classification, confidentiality controls AI security testing, agent governance, runtime
Manufacturing
49
Developing OT/IT security baseline AI-specific controls broadly, agent security
Retail & E-commerce
46
Developing Fraud detection, PCI DSS controls RAG security, agent governance, supply chain
SMB Average
38
Ad Hoc →
Developing
Agility, modern cloud-native stack Governance broadly, no dedicated security team

† Coverage scores are structured analyst estimates based on framework analysis and typical deployment patterns. Individual organisations may score significantly above or below their industry average based on security programme maturity, AI adoption pace, and investment level.

Section 5 — Maturity Framework

The HexTyx AI Security Maturity Model

Based on the NIST AI RMF conceptual structure and adapted for AI-specific security practice, the five-level maturity model provides organisations with a progression framework from baseline awareness to industry-leading AI security operations. Most enterprises currently operate at Level 2 (Developing) to Level 3 (Managed).

1

Ad Hoc 0 – 25

AI is deployed without systematic security consideration. Controls are absent or entirely reactive. No AI inventory exists. No incident response procedures for AI-specific events. This is the default state for most organisations at the moment they first deploy generative AI.

  • No AI security policies or governance
  • No security testing of AI systems
  • No AI asset inventory
  • Reactive response to incidents only
2

Developing 26 – 50

Basic security controls are in place. AI awareness has entered the security conversation. Some testing exists but is not systematic. Governance is primarily reactive — policies are written after incidents rather than before deployment.

  • Basic AI policy documentation
  • Limited security testing (often manual)
  • Partial AI inventory maintained
  • General vendor reviews not AI-specific
3

Managed 51 – 70

A formal AI security programme exists. Security testing is conducted before deployment and on a regular cadence. Governance includes risk assessment, documented ownership, and compliance mapping. Monitoring is present but may not be AI-specific.

  • Pre-deployment security reviews mandatory
  • AI risk assessments documented
  • Governance framework in place
  • Compliance framework mapping completed
4

Optimised 71 – 85

Continuous security testing, runtime monitoring, and formal ownership assignment are standard practice. Red teaming is conducted at least annually. AI security metrics are tracked and reported to leadership. Agent security and RAG security have dedicated controls.

  • Continuous AI security testing
  • AI-specific runtime monitoring deployed
  • Regular AI red team exercises
  • Executive-level AI risk reporting
5

AI-First Security 86 – 100

AI security is a first-class discipline with dedicated resources, specialised expertise, and continuous improvement driven by benchmark data and proprietary threat intelligence. Automated governance, continuous red teaming, and benchmark-driven improvement cycles define operations at this level. A small minority of organisations currently achieve this maturity.

  • Dedicated AI security team and expertise
  • Continuous red teaming and automated testing
  • Proprietary benchmark data drives decisions
  • AI security is a board-level governance function
Section 6 — Risk Register

Top 10 AI Security Risks for 2026

Derived from the intersection of MITRE ATLAS technique frequency, OWASP GenAI community prioritisation, and observed enterprise incident patterns. These risks represent the threats most likely to result in a material security incident for an enterprise AI deployment in 2026.

1

Prompt Injection

The foundational AI attack. Direct and indirect variants both active.

MITRE AML.T0051 · OWASP LLM01
2

Agent Goal Hijacking

Adversary redirects autonomous agent objectives via instruction override.

OWASP Agentic · MITRE AML.T0080
3

Tool Abuse

Agent manipulated to misuse legitimate API and tool access.

MITRE AML.T0080 · OWASP LLM06
4

Sensitive Data Leakage

PII, PHI, IP extracted through AI outputs or retrieval disclosure.

MITRE AML.T0057 · OWASP LLM02
5

Retrieval Poisoning

Malicious content injected into RAG knowledge base corrupts AI outputs.

MITRE AML.T0086 · OWASP LLM08
6

Excessive Agency

Agent granted more capability than required for its defined function.

OWASP LLM06 · MITRE AML.T0082
7

Supply Chain Compromise

Third-party model, plugin, or MCP server becomes an attack vector.

MITRE AML.T0010 · OWASP LLM05
8

Model Theft

Proprietary model capability extracted through repeated adversarial querying.

MITRE AML.T0006 · OWASP LLM09
9

Governance Failure

AI deployed without policy, oversight, inventory, or incident response.

NIST AI RMF GOVERN · EU AI Act Art.9
10

Shadow AI

Employees use unapproved AI tools that process sensitive enterprise data.

OWASP GenAI · NIST AI RMF MAP
Section 7 — Key Findings

Four Findings That Define the 2026 Landscape

Finding 1 — Agent Security Is the Largest Structural Gap

At 41/100, agent security is the lowest-scoring domain — and the domain with the fastest-growing enterprise adoption. Organisations are deploying autonomous agents for customer service, sales outreach, code generation, and operations without the security controls that the attack surface requires. Tool permission governance, MCP security validation, and agent memory controls are not yet standard practice in any industry sector.

The critical asymmetry: The blast radius of a compromised AI agent is dramatically larger than a compromised chatbot. A chatbot that misbehaves generates a bad response. An agent that is hijacked can send emails, modify records, call external APIs, and trigger business processes — all using its own legitimate credentials, producing no authentication anomalies for traditional security monitoring to detect.

Finding 2 — Governance Adoption Lags AI Deployment by 12–18 Months

AI deployment is accelerating faster than governance maturity across every sector assessed. The pattern is consistent: AI tools are adopted by individual departments or engineering teams, then security and compliance teams are asked to assess and govern systems that are already in production. Pre-deployment security review — the most efficient point to address AI risk — is not yet standard practice outside of technology-sector organisations.

Finding 3 — Supply Chain Risk Is the Most Underestimated Threat Category

At 39/100, AI supply chain security scores below even agent security — despite the fact that most enterprise AI systems are built almost entirely from third-party components. Foundation models, inference APIs, vector databases, orchestration frameworks, and MCP connectors are all external dependencies with their own security postures, data handling terms, and vulnerability exposure. Yet most enterprise AI vendor assessments evaluate SLAs, data handling, and pricing — not model security, inference-time attack resilience, or supply chain transparency.

Finding 4 — RAG Security Has Not Kept Pace With RAG Adoption

Enterprise RAG adoption has outpaced the development of RAG-specific security controls. Data access controls govern who can read files. They don't automatically govern which chunks a vector retrieval system returns, whether cross-tenant isolation is enforced, or whether the knowledge base has been integrity-validated. These are architectural security problems that require RAG-specific tooling and controls that most enterprises have not yet implemented.

Section 8 — Forward Outlook

Five Developments That Will Define AI Security in 2027

2027

Agent Security Becomes a Dedicated Security Category

Autonomous agent deployments will reach critical mass in enterprise environments in 2026–2027. The security failures that result — and there will be documented, public failures — will drive the emergence of agent security as a recognised discipline, with dedicated tooling, standards, and practitioner expertise analogous to how cloud security emerged from cloud adoption in 2013–2016. OWASP's Agentic Security Initiative is the early signal of this categorisation.

2027

AI Supply Chain Reviews Become Standard Enterprise Procurement Requirements

Enterprise security questionnaires will expand to include AI-specific vendor assessment criteria: model provenance, training data governance, inference security, and model version change management. Vendors who cannot answer these questions will face procurement friction. This shift mirrors what happened with cloud security questionnaires in 2015–2018 and SOC 2 requirements in 2018–2022.

2027

AI Red Teaming Transitions from Optional to Routine

Regulatory pressure (EU AI Act, US Executive Order on AI), insurance requirements, and customer security questionnaires will drive AI red teaming from an advanced practice to a standard expectation for any organisation deploying high-risk AI systems. The question will shift from "should we red team our AI?" to "how often are you red teaming, and what is your methodology?"

2027

Runtime Monitoring Becomes Mandatory for High-Risk AI Systems

The EU AI Act's Article 9 risk management system requirements, combined with NIST AI RMF MEASURE and MANAGE function obligations, will drive runtime monitoring from a security best practice to a compliance requirement for high-risk AI system operators. The monitoring gap — currently one of the largest in the AI security landscape — will close rapidly under regulatory and contractual pressure.

2027

AI Security Benchmarks Become as Common as Vulnerability Management Benchmarks

The question "what is our CVSS average?" has been a standard board-level security metric for a decade. By 2027, equivalent AI security metrics — MITRE ATLAS coverage percentage, agent security maturity level, RAG security posture score — will enter regular board and executive reporting. This benchmark is an early contribution to that emerging measurement ecosystem.

Conclusion

From Baseline to Proprietary Intelligence

The 2026 AI threat landscape is no longer dominated solely by prompt injection. Enterprises face a broader attack surface encompassing autonomous agents, retrieval systems, supply chains, governance failures, and increasingly complex AI ecosystems — most of which their current security programmes were not designed to address.

This inaugural benchmark establishes a structured framework built on six authoritative sources and provides a reproducible methodology that becomes more precise as proprietary data accumulates. The Q4 2026 edition of this report will incorporate real usage data from the AIZA-HexTyx free tool platform, transforming analyst estimates into statistically grounded benchmarks.

"The organisations that will lead AI security in 2027 are not the ones that deploy AI most aggressively. They are the ones that measure their posture, benchmark against peers, and systematically close the gaps that measurement reveals."

AIZA-HexTyx Research, 2026 — AI Security Threat Landscape & Coverage Benchmark

The tools to measure that posture are available now — free, and built specifically for the AI security challenges this report describes.

Measure Your Coverage Benchmark Your Industry ️ Map Your Controls ️ Explore the Threat Landscape

Citation: AIZA-HexTyx. (2026). AI Security Threat Landscape & Coverage Benchmark 2026 (Version 1.0). AIZA-HexTyx Research. https://hextyx.com/ai-security-benchmark-report-2026.html

Licence: Free to cite with attribution. Charts and figures may be reproduced with "Source: AIZA-HexTyx AI Security Benchmark 2026 (hextyx.com)" credit line.