OWASP Top 10 for LLM Applications 2026

LLM threat catalogue (incl. Excessive Agency at #3)

By Jorge García Aibar Reviewed 2026-09-24

From clause to evidence Build the artefact, then file every output it produces as a record that names AIGE-OBL-OWASP-LLM. Drawn from chapter 08.

Text alternative

Clause: OWASP LLM, Top 10 for LLM….
Duty holder: Not stated.
Applies from: No date, Voluntary.
Artefact: Prompt-injection and output-handling controls.
Layers: Layer 03, Layer 04.
Evidence record: Evidence record v1.
Record schema: Evidence record.
The same topic in 22 other frameworks; the crosswalk section below links each clause.

Id: AIGE-OBL-OWASP-LLM
Instrument: OWASP Top 10 for LLM Applications 2026 framework
Clause: Top 10 for LLM Applications 2026
Applies from: No date Voluntary · Voluntary (2026 edition)

The artefact that evidences it

Prompt-injection and output-handling controls; eval gate.

Patterns that build it

AI Threat Model (layer 1 and 3)
Dataset Admission Gate (layer 1 and 2)
Model Artefact Integrity (layer 2 and 4)
Rights Requests Against Models (layer 2 and 5)
Sanctioned AI Gateway (layer 4 and 2)
Downstream Use Register (layer 2 and 1)

The same topic in other frameworks

From the topic crosswalk: the clauses filed under the same topics as this one. Mappings are illustrative, not a claim of conformity.

Data governance

EU AI Act Art. 10 Data and data governance (core)
ISO 42001 A.7 Data for AI systems (core)
TC260 Framework 3.0 TC260 2.1.3 Data safety risks (core)
China GenAI Measures GenAI Art. 7 Training-data lawful sourcing (core)
China GenAI Measures GenAI Art. 8 Data-annotation standards (core)
China GenAI Measures GenAI Art. 11 Protection of user input and records (core)
China Deep Synthesis DeepSyn Art. 14 Training-data management (core)
GB/T 45654 GB/T 45654 Corpus security Training-corpus (data) security requirements (core) (clause not verified)
EU AI Act Art. 10(2)(f)–(g) Examination for possible biases; measures to detect, prevent and mitigate them (core)
GDPR Art. 5(1)(c) Data minimisation (core)
GDPR Art. 25 Data protection by design and by default (core)
ISO 42001 A.7.3 Acquisition of data (core) (clause not verified)
CSA AICM DSP-20 Data Provenance and Transparency (core)
UK ATRS ATRS 2.4.3 Development data specification (core)
Singapore GenAI GenAI 2 Data (core)
GAO AI Accountability 2.1 Sources: document sources and origins of data used to develop the models (core)
GAO AI Accountability 2.2 Reliability: assess reliability of data used to develop the models (core)
EU AI Act Art. 4a Special-category data for bias detection
ISO 42001 A.4 Resources for AI systems
NIST AI RMF MAP 2 MAP 2: Categorization of the AI system is performed
NIST AI RMF MEASURE 2.10 MEASURE 2.10: Privacy risk of the AI system is examined and documented
NIST AI RMF MEASURE 2.11 MEASURE 2.11: Fairness and bias are evaluated and results are documented
TC260 Framework 3.0 TC260 5.1 Model R&D safety guidelines
EU AI Act Art. 53 Obligations for providers of general-purpose AI models
EU AI Act Art. 53(1)(c) Copyright policy, including rights reservations
EU AI Act Art. 5(1)(e) Prohibited: untargeted scraping of facial images
GPAI Code Copyright 1.1–1.5 Commitment 1: Copyright policy (Measures 1.1 to 1.5)
GDPR Art. 9 Processing of special categories of personal data
CSA AICM DSP-21 Data Poisoning Prevention & Detection
GAO AI Accountability 2.4 Variable selection: assess data variables used in the AI component models
GAO AI Accountability 2.5 Enhancement: assess the use of synthetic, imputed, and/or augmented data

Runtime guardrails

ISO 42001 A.9 Use of AI systems (core)
NIST AI RMF MANAGE 2 MANAGE 2: Strategies to maximize AI benefits and minimize negative impacts are planned, prepared, implemented, documented, and informed by relevant AI actors (core)
TC260 Framework 3.0 TC260 App. 2 II.5 Dynamic runtime management (core)
TC260 Framework 3.0 TC260 3.2.1 Technological countermeasures for agentic AI (core)
China GenAI Measures GenAI Art. 10 Guided, bounded use (core)
China GenAI Measures GenAI Art. 14 Stop unlawful generation (core)
China Deep Synthesis DeepSyn Art. 10 Input and output review (core)
CSA AICM TVM-13 Guardrails (core)
CSA AICM AIS-09 Input Validation (core)
CSA AICM AIS-10 Output Validation (core)
Singapore Agentic Agentic 2.3.1 During design and development, use technical controls (core)
EU AI Act Art. 5 Prohibited AI practices
EU AI Act Art. 15 Accuracy, robustness and cybersecurity
ISO 42001 A.6 AI system life cycle
China Algo. Rec. AlgoRec Art. 8 Periodic algorithm review
China Algo. Rec. AlgoRec Art. 9 Feature database for unlawful content
EU AI Act Art. 5(1)(a)–(b) Manipulative techniques; exploitation of vulnerabilities
GPAI Code Safety C5 Commitment 5: Safety mitigations

Robustness, security and evaluations

EU AI Act Art. 15 Accuracy, robustness and cybersecurity (core)
EU AI Act Art. 55 Obligations for providers of general-purpose AI models with systemic risk (core)
ISO 42001 A.6 AI system life cycle (core)
NIST AI RMF MEASURE 2 MEASURE 2: AI systems are evaluated for trustworthy characteristics (core)
TC260 Framework 3.0 TC260 3 Technological countermeasures (core)
TC260 Framework 3.0 TC260 App. 2 II.6 Sandbox validation and red teaming (core)
China Deep Synthesis DeepSyn Art. 15 Technology management and algorithm verification (core)
China Deep Synthesis DeepSyn Art. 20 Security assessment of new products (core)
GB/T 45654 GB/T 45654 Security assessment Security-assessment requirements for generative AI services (core) (clause not verified)
GPAI Code Safety 3.2 Measure 3.2: Model evaluations (core)
NIST AI RMF MEASURE 2.7 MEASURE 2.7: AI system security and resilience as identified in the MAP function are evaluated and documented (core)
CSA AICM MDS-06 Adversarial Attack Analysis (core)
CSA AICM MDS-07 Robustness against Adversarial Attack / Model Hardening (core)
Singapore GenAI GenAI 5 Testing and Assurance (core)
Singapore GenAI GenAI 6 Security (core)
Singapore Agentic Agentic 2.3.2 Before deploying, test agents (core)
CoE Convention CoE Art. 16(2)(g) Testing before first use and when significantly modified (core)
OECD AI Principles OECD 1.4 Robustness, security and safety (core)
G7 Code G7 Action 1 Identify, evaluate and mitigate risks across the lifecycle, including testing (core)
GAO AI Accountability 3.7 Assessment: assess performance against defined metrics to ensure the AI system functions as intended and is sufficiently robust (core)
EU AI Act Art. 60 Testing of high-risk AI systems in real-world conditions outside AI regulatory sandboxes
ISO 42001 9.1 Monitoring, measurement, analysis and evaluation
TC260 Framework 3.0 TC260 5.3.14 Resilience
China GenAI Measures GenAI Art. 17 Security assessment
EU AI Act Art. 15(3) Declared accuracy levels and metrics
EU AI Act Art. 9 Risk management system
EU AI Act Art. 42(3) Presumption of conformity for cybersecurity (Cyber Resilience Act)
GPAI Code Safety C6 Commitment 6: Security mitigations
GDPR Art. 32 Security of processing
NIST AI RMF MEASURE 2.1 MEASURE 2.1: Test sets, metrics, and details about the tools used during TEVV are documented
NIST AI RMF MEASURE 1 MEASURE 1: Appropriate methods and metrics are identified and applied
CSA AICM AIS-05 Application Security Testing
OWASP Agentic ASI05 Unexpected Code Execution (RCE)
Korea AI Act Art. 32(1) Safety duties for AI above the compute threshold
GAO AI Accountability 3.2 Metrics: define performance metrics that are precise, consistent, and reproducible

Supply chain and third parties

EU AI Act Art. 25 Responsibilities along the AI value chain (core)
ISO 42001 A.10 Third-party and customer relationships (core)
NIST AI RMF GOVERN 6 GOVERN 6: Policies and procedures are in place to address AI risks and benefits arising from third-party software and data and other supply chain issues (core)
NIST AI RMF MAP 4 MAP 4: Risks and benefits are mapped for all AI system components including third-party software and data (core)
NIST AI RMF MANAGE 3 MANAGE 3: AI risks and benefits from third-party entities are managed (core)
TC260 Framework 3.0 TC260 App. 2 II.4 Supply chain and tool management (core)
EU AI Act Art. 25(4) Written agreement with third-party suppliers (core)
GDPR Art. 28 Processor (core)
NIST AI RMF MANAGE 3.1 MANAGE 3.1: AI risks and benefits from third-party resources are regularly monitored, and risk controls are applied and documented (core)
CSA AICM STA-10 Supply Chain Risk Management (core)
CSA AICM STA-09 Service Bill of Material (BOM) (core)
OWASP Agentic ASI04 Agentic Supply Chain Vulnerabilities (core)
EU AI Act Art. 26 Obligations of deployers of high-risk AI systems
TC260 Framework 3.0 TC260 4.4.4 Open-source ecosystem
China GenAI Measures GenAI Art. 7 Lawful data and model sources
China Deep Synthesis DeepSyn Art. 14 Providers and technical supporters
EU AI Act Art. 22 Authorised representatives of providers of high-risk AI systems
EU AI Act Art. 23 Obligations of importers
EU AI Act Art. 24 Obligations of distributors
EU AI Act Art. 54 Authorised representatives of providers of general-purpose AI models
GPAI Code Transparency 1.2 Providing relevant information
GDPR Arts. 44–46 Transfers to third countries
NIST AI RMF GOVERN 6.2 GOVERN 6.2: Contingency processes are in place to handle failures or incidents in third-party data or AI systems deemed to be high-risk
UK ATRS ATRS 2.1.4 Third party involvement
G7 Code G7 Action 11 Implement data input measures and protect personal data and intellectual property
GAO AI Accountability 2.6 Dependency: assess interconnectivities and dependencies of data streams that operationalize the AI system

Privacy and data protection

GDPR Art. 5 Principles relating to processing of personal data (core)
GDPR Art. 6 Lawfulness of processing (core)
GDPR Art. 25 Data protection by design and by default (core)
NIST AI RMF MEASURE 2.10 MEASURE 2.10: Privacy risk of the AI system as identified in the MAP function is examined and documented (core)
CSA AICM DSP-08 Data Privacy by Design and Default (core)
CoE Convention CoE Art. 11 Privacy and personal data protection (core)
China GenAI Measures GenAI Art. 7(3) Consent or another lawful basis for personal information in training data (core)
China GenAI Measures GenAI Art. 11 Protection of user input and records (core)
GAO AI Accountability 2.8 Security and privacy: assess data security and privacy for the AI system (core)
EU AI Act Art. 59 Further processing of personal data in the AI regulatory sandbox
EU AI Act Art. 4a Special-category data for bias detection
GDPR Art. 35 Data protection impact assessment
ISO 42001 A.7 Data for AI systems
CSA AICM DSP-22 Privacy Enhancing Technologies
UK DUAA UK GDPR Art. 22B Restrictions on automated decision-making
Singapore GenAI GenAI 2 Data
OECD AI Principles OECD 1.2 Rule of law, human rights and democratic values, including fairness and privacy
G7 Code G7 Action 11 Implement data input measures and protect personal data and intellectual property

Agent identity and autonomy

CSA AICM IAM-18 Agent Access Restriction (core)
CSA AICM AIS-11 Agents Security Boundaries (core)
OWASP Agentic ASI03 Identity and Privilege Abuse (core)
Singapore Agentic Agentic 2.1.2 Bound risks through design by defining agents limits and permissions (core)
TC260 Framework 3.0 TC260 App. 2 II.2 Identity and access management (core)
EU AI Act Art. 14 Human oversight
NIST AI RMF GOVERN 3.2 GOVERN 3.2: Policies and procedures are in place to define and differentiate roles and responsibilities for human-AI configurations and oversight of AI systems
CSA AICM IAM-12 Unique Identities
OWASP Agentic ASI02 Tool Misuse and Exploitation
OWASP Agentic ASI07 Insecure Inter-Agent Communication
OWASP Agentic ASI10 Rogue Agents
Singapore Agentic Agentic 2.2.2 Design for meaningful human oversight
TC260 Framework 3.0 TC260 App. 2 II.3 Strengthen human approval

Content provenance and deepfakes

EU AI Act Art. 50(2) Machine-readable marking of synthetic content (core)
EU AI Act Art. 50(4) Disclosure of deep fakes (core)
Korea AI Act Art. 31 Transparency: prior notice, output labelling, realistic synthetic content (core)
Singapore GenAI GenAI 7 Content Provenance (core)
G7 Code G7 Action 7 Deploy content authentication and provenance mechanisms where feasible (core)
China AI Labelling Label Art. 4 Explicit labels for generated content (core)
China AI Labelling Label Art. 5 Implicit (metadata) labels (core)
China Deep Synthesis DeepSyn Art. 17 Conspicuous labels for confusable content (core)
EU AI Act Art. 3(60) Definition of deep fake
CSA AICM MDS-09 Model Signing/Ownership Verification
China GenAI Measures GenAI Art. 12 Labelling of generated content

Open controls that evidence it

Draft controls in the open control profiles that map to this row: each states a requirement and the evidence it must leave behind.

AIGE-CTL-EVAL-002 Network Egress Control (Evaluation environment profile)
AIGE-CTL-DATA-009 Signed Snapshot Integrity (Data admission and privacy profile)
AIGE-CTL-ASSURE-010 Model Artefacts Signed at Build and Verified Before Load (Assurance and evidence profile)
AIGE-CTL-ASSURE-011 Safe Model Formats and Digest-Pinned Third-Party Models (Assurance and evidence profile)

Source

Chapter 08, section OWASP GenAI Security Project, checked against its sources on the review date above.

Machine-readable

This obligation: /api/v1/obligations/aige-obl-owasp-llm.json
The register: /api/v1/obligations.json · CSV
Schema and stability promise: open data and API

Cite this obligation

García Aibar, J. (2026). OWASP Top 10 for LLM Applications 2026 (AIGE-OBL-OWASP-LLM). In AI Governance Engineering: The Thesis & Body of Knowledge (v0.5.0). https://doi.org/10.5281/zenodo.22956197. https://aigovernanceengineer.com/obligations/aige-obl-owasp-llm. CC BY 4.0

BibTeX

@misc{aige2026obligation,
  author       = {Jorge García Aibar},
  title        = {{OWASP Top 10 for LLM Applications 2026 (AIGE-OBL-OWASP-LLM)}},
  howpublished = {In AI Governance Engineering: The Thesis \& Body of Knowledge},
  year         = {2026},
  version      = {0.5.0},
  doi          = {10.5281/zenodo.22956197},
  url          = {https://aigovernanceengineer.com/obligations/aige-obl-owasp-llm},
  note         = {Version 0.5.0}
}