Source directoryEuropean Union (EUR-Lex)OJ L 2024/1689, 12.07.2024

Regulation (EU) 2024/1689 (Artificial Intelligence Act), authentic Official Journal text

“Regulation (EU) 2024/1689 (Artificial Intelligence Act), authentic Official Journal text”. Publisher: European Union (EUR-Lex). Version used: OJ L 2024/1689, 12.07.2024. The Versatile AI Risk Assessment threat catalogue backs 51 of its 52 threats with this document, at 15 verified locations.

As of: July 2026 · Catalogue version 2026.07.17.3

Document details

Publisher: European Union (EUR-Lex)
Version used: OJ L 2024/1689, 12.07.2024
Year: not stated
Licence: not stated
Framework: EU AI Act

Open the original document at the publisher External link; the publisher’s version always takes precedence.

References in the catalogue (15)

Every row states the clause, its title, the exact location in the document and the threats that refer to it.

Clauses of this document with the threats that reference them
Clause	Title and location	Referencing threats
`Article 13(1), 13(3)(b)(ii), (iv), (v)`	Transparency and provision of information to deployers Article 13(1), 13(3)(b)(ii), (iv), (v)	Sensitive Information Disclosure Exfiltration from ML Application Overreliance Factual Inconsistencies (Hallucinations)
`Article 14(4)(b)`	Human oversight Article 14(4)(b)	Overreliance
`Article 14(4)(d)`	Human oversight Article 14(4)(d); for automation bias, Article 14(4)(b)	Prompt Injection – Direct Prompt Injection – Indirect Insecure Tool Design Excessive Agency Agentic AI / Autonomous Agents MCP Hijacking (Model Context Protocol)
`Article 15(5)`	Accuracy, robustness and cybersecurity Article 15(5), including the express references to data/model poisoning, adversarial examples/evasion, confidentiality attacks and model flaws	Agent Memory Poisoning (Persistent Context)Insecure Inter-Agent Communication (A2A/MCP)
`Article 25(4)`	Responsibilities along the AI value chain Article 25(4)	Supply Chain – Infrastructure Supply Chain – Models Supply Chain – Datasets RAG-Specific Attacks (Document Poisoning)Middleware Exploits (AI Framework Attacks)
`Article 26(5)`	Obligations of deployers of high-risk AI systems Article 26(5)	Adversarial Inputs Model Denial of Service Cost Harvesting / Repurposing Application Denial of Service Agentic AI / Autonomous Agents Model Drift & Degradation Agent Memory Poisoning (Persistent Context)
`Article 4`	AI literacy Article 4	Overreliance Shadow AI (Unsanctioned AI Service Use)
`Article 5(1)(a)`	Prohibited AI practices Article 5(1)(a); where the catalogue cites exploitation, compare Article 5(1)(b)	Unethical Actions Social Engineering Fraud Disinformation
`Article 50(2), 50(4)`	Transparency obligations for providers and deployers of certain AI systems Article 50(2) and 50(4)	Disinformation
`Article 53(1)(a)`	Obligations for providers of general-purpose AI models Article 53(1)(a) and Annex XI	Supply Chain – Infrastructure Supply Chain – Models Supply Chain – Datasets Backdoor ML Model Sleepy Agent (Time/Event-Triggered Hidden Instructions)
`Article 53(1)(d)`	Obligations for providers of general-purpose AI models Article 53(1)(d)	Supply Chain – Datasets Training Data Poisoning Targeted Poisoning / Label Poisoning
`Article 55(1)(a)`	Obligations of providers of general-purpose AI models with systemic risk Article 55(1)(a)	Training Data Poisoning Targeted Poisoning / Label Poisoning Backdoor ML Model Sleepy Agent (Time/Event-Triggered Hidden Instructions)Adversarial Inputs Prompt Injection – Direct Prompt Injection – Indirect Jailbreaks Meta Prompt Extraction Privacy Attacks Misalignment Agentic AI / Autonomous Agents Multimodal Attacks
`Article 55(1)(b)`	Obligations of providers of general-purpose AI models with systemic risk Article 55(1)(b)	Jailbreaks Sensitive Information Disclosure Hate Speech and Discrimination Sexual Content Violence / Unsafe Actions Controversial Topics Illegal Activities Self-harm Harassment Unethical Actions Social Engineering Fraud Malicious Software Disinformation Misalignment Model Drift & Degradation
`Article 55(1)(d)`	Obligations of providers of general-purpose AI models with systemic risk Article 55(1)(d)	Supply Chain – Infrastructure Supply Chain – Models Model Theft Model Denial of Service Cost Harvesting / Repurposing Exfiltration from ML Application Application Vulnerabilities Application Denial of Service Multimodal Attacks Model Reconnaissance Middleware Exploits (AI Framework Attacks)Side-Channel Attacks (Timing Analysis)
`Article 9(1), 9(2)(a), 9(2)(d)`	Risk management system Article 9(1), 9(2)(a), 9(2)(d), read with Article 9(3)	Training Data Poisoning Backdoor ML Model Sleepy Agent (Time/Event-Triggered Hidden Instructions)Adversarial Inputs Jailbreaks Model Denial of Service Cost Harvesting / Repurposing Exfiltration from ML Application Insecure Output Handling Insecure Tool Design Application Vulnerabilities Application Denial of Service Excessive Agency Controversial Topics Unethical Actions Social Engineering Malicious Software Factual Inconsistencies (Hallucinations)Misalignment Agentic AI / Autonomous Agents RAG-Specific Attacks (Document Poisoning)Multimodal Attacks Middleware Exploits (AI Framework Attacks)Cross-Tenant Leakage (Multi-Tenant Vector DB)MCP Hijacking (Model Context Protocol)Side-Channel Attacks (Timing Analysis)Graph-RAG Poisoning (Knowledge Graph Injection)Agent Memory Poisoning (Persistent Context)Insecure Inter-Agent Communication (A2A/MCP)

This page does not reproduce the text of the standards. It states the identifier, title and location of the clause; the wording itself is in the original document. The mappings are taxonomic and not evidence of compliance.

Threats referencing this document (51)

Grouped by topic. Every entry leads to the full threat page.

Agentic and Autonomous AI

Application and Integration Security

Attacks on the Running Model and Service

Harmful Content

Malicious Use for Attacks, Fraud and Disinformation

Model and Training Data Manipulation

Privacy and Data Leakage

Prompt Attacks and Guardrail Evasion

Reliability and Responsible Use

Supply Chain and Provenance

From the reference to the assessment

The full catalogue states the mitigations, the possible impact and every verified location for each threat. The live demo runs locally in your browser, with no sign-up.

Go to the threat catalogue Start the live demo

Cite this page

For reports, policies or internal documents; the link leads directly to this source page.

“Regulation (EU) 2024/1689 (Artificial Intelligence Act), authentic Official Journal text” (European Union (EUR-Lex)). References in the AI threat catalogue, Versatile AI Risk Assessment, as of July 2026.
https://www.versatile-ai-risk-assessment.com/en/wissensbasis/sources/eu-ai-act-2024-1689/

← Back to the source directory