⭐ Star on GitHub

Summary: Where each OWASP entry lands in PITAX, ATLAS, the AI Act and this vault’s collections. OWASP is the lingua franca the other frameworks assume.

Sources: raw/OWASP-Top-10-for-LLMs/; cross-referenced against PITAX, ATLAS 2026.06, Regulation (EU) 2024/1689

Last updated: 2026-07-29


The master table

OWASP 2025PITAXATLASAI Act Art 15(5)Vault collection
LLM01 Prompt InjectionAll 70 techniquesAML.T0051 (+.000/.001/.002)not namedAttack Techniques
LLM02 Sensitive Info DisclosureT58 oracle extractionExfiltration tacticconfidentiality attacksModel Theft
LLM03 Supply ChainT46 instruction-file injectionResource Developmentmodel poisoningSupply Chain
LLM04 Data & Model PoisoningT13, T32, T44, T64Resource Developmentdata poisoningData Poisoning
LLM05 Improper Output HandlingT63 structured-output coercionExecutionnot namedSecure Coding
LLM06 Excessive AgencyT42, T43, T47, T53, T65, T69, T70AML.T0053not namedAgentic attacks
LLM07 System Prompt LeakageT58, T05 CoT introspectionDiscovery tacticnot named
LLM08 Vector & EmbeddingT64, T13Resource Developmentnot namedRAG poisoning
LLM09 MisinformationT57, T67 (offensive use)Impact tacticnot named
LLM10 Unbounded ConsumptionT09, T41 (query-hungry attacks)AI Model Accessconfidentiality attacksModel Theft

What the crosswalk exposes

Six of ten OWASP entries have no counterpart in AI Act Art 15(5). The Act names five attack classes drawn from the adversarial-ML canon — data poisoning, model poisoning, adversarial examples, confidentiality attacks, model flaws. Prompt injection, improper output handling, excessive agency, system prompt leakage, vector weaknesses and misinformation are all absent by name.

This is the third independent line of evidence for the same conclusion already recorded in Article 15:

  1. PITAX has 6 purely-indirect techniques, all targeting agent infrastructure.
  2. ATLAS tags 114 techniques as Agentic AI — its largest platform category.
  3. OWASP devotes three of ten entries (LLM05, LLM06, LLM08) to agent and retrieval plumbing.

Three taxonomies built by different communities converge on an attack surface the Regulation does not name.

LLM01 is not a peer of the others. It maps to all 70 PITAX techniques and to one ATLAS technique. As a risk-register line item it is fine; as a unit of analysis it is far too coarse. Anyone working on prompt injection needs PITAX underneath it.

Granularity comparison

FrameworkPrompt injection is…Total objects
OWASP1 of 10 entries10
ATLAS1 technique + 3 sub-techniques173 techniques
PITAXthe entire taxonomy70 techniques

Each is correctly scoped for its job. OWASP names the risk for a board; ATLAS places it in an attack chain for a SOC; PITAX describes the payload for a red team.

Where OWASP is the best source in the vault

Two entries carry material nothing else here covers:

  • LLM03 Supply Chain uniquely covers LoRA/PEFT fine-tuning risk on model hubs and on-device LLM exposure — detail absent from the Supply Chain Attacks collection, whose taxonomy operates a layer above.
  • LLM05 Improper Output Handling frames LLM output as untrusted input flowing into XSS, CSRF, SSRF and RCE — the bridge to conventional appsec, which neither PITAX nor ATLAS offers. Securing LLM applications implements this layer.

LLM04 also contributes two things the dedicated Data Poisoning collection lacks: malicious pickling (code execution on model load, not model misbehaviour) and the sleeper agent framing for trigger-gated backdoors.

Regulatory usage

Microsoft’s IR readiness pattern cites the OWASP Top 10 for LLMs under severity adaptation — supplementing “traditional metrics with contextual factors: domain, user population, content nature, and misuse potential” (source: raw/AI-incident-response/Incident response for AI systems.md).

That is the practical role: an incident taxonomy vocabulary for AI-specific harm categories, which is exactly what Microsoft identifies as missing when “incidents default to generic buckets.” See Microsoft IR readiness.