Explore our new Cybersecurity Terms Glossary, explained by our experts.

View the Glossary View the Glossary
PRIVIA

Cybersecurity Terms Glossary

What Is the OWASP LLM Top 10?

The OWASP Top 10 for LLM Applications is a community-maintained list of the most critical security risks in applications built on large language models.

Illustration for the cybersecurity term OWASP LLM Top 10
Home / Blog / Cybersecurity Terms / What Is the OWASP LLM Top 10?
17 November 2026

What Is the OWASP LLM Top 10?

What Is the OWASP LLM Top 10?

The OWASP Top 10 for LLM Applications does for AI software what the original OWASP Top 10 did for web applications: it gives developers, testers, and procurement teams a common list of what goes wrong most often. First published in 2023 and substantially revised for the 2025 edition, it is maintained by practitioners reporting from real deployments rather than derived from theory, which is why the entries read like incident summaries.

The 2025 List

IDRiskIn one line
LLM01Prompt InjectionCrafted input overrides the application’s instructions
LLM02Sensitive Information DisclosureThe model reveals data it should not, from context, memory, or training
LLM03Supply ChainCompromised models, datasets, adapters, or dependencies
LLM04Data and Model PoisoningCorrupted training or fine-tuning data implants a behaviour
LLM05Improper Output HandlingModel output reaches a browser, shell, or database unvalidated
LLM06Excessive AgencyToo much permission, functionality, or autonomy
LLM07System Prompt LeakageHidden instructions, and the secrets placed in them, are exposed
LLM08Vector and Embedding WeaknessesRetrieval and embedding stores leak or are manipulated
LLM09MisinformationConfident false output, compounded by over-reliance
LLM10Unbounded ConsumptionRunaway tokens, cost, and resource use

What the 2025 Revision Changed

Three entries are new or substantially reframed, and each reflects what practitioners actually encountered. System prompt leakage was promoted to its own entry after a year in which hidden instructions turned out to contain credentials, business rules, and internal URLs rather than just personality guidance. Vector and embedding weaknesses arrived because retrieval-augmented generation became the default architecture, bringing permission bypass, poisoned documents, and the inversion risks described in our note on embedding inversion. Unbounded consumption replaced the narrower denial-of-service framing to include the commercial reality that token spend is now an attack surface. Meanwhile denial of service and overreliance from the 2023 edition were folded into other entries.

Using It Rather Than Citing It

The list earns its value as a working tool in four places. In design review, walk a proposed architecture through each entry and note where a control exists and where it does not—LLM05 and LLM06 usually expose the most. In test scoping, require that an assessment covers all ten explicitly, because a report that only lists prompt injection findings has probably not looked at output handling or consumption limits. In procurement, ask a vendor to state how their product addresses each entry; the quality of the answer is informative regardless of the content. And in developer training, it provides a vocabulary that security and engineering can share, which is most of what makes a secure development process work.

Its Limits

It is a list of common risks, not a standard, a certification, or a complete threat model. It says nothing about model bias or safety, barely touches governance, and does not replace conventional application security testing of the same system—most LLM applications still fail on authentication, authorisation, and dependency management before anything AI-specific. Pair it with MITRE ATLAS for adversary techniques, NIST AI 100-2 for attack taxonomy, and the NIST AI Risk Management Framework for governance. OWASP has also published companion material on agentic systems and on securing generative AI deployments, which extends the coverage towards AI agent security.

For UK Organisations

Referencing the list is a straightforward way to evidence that you considered known AI risks, which supports UK GDPR accountability and sits comfortably alongside NCSC and CISA guidance on secure AI development. For organisations facing the EU AI Act, it offers a practical reading of what Article 15’s cybersecurity requirement means in engineering terms. At Privia Security, we structure our AI Penetration Test Services around all ten entries plus the conventional application layer beneath them.

FAQ – Frequently Asked Questions

How Is This Different From the Original OWASP Top 10?

The original covers web application vulnerabilities such as broken access control and injection, and it still applies to any AI application, because those are web applications too. The LLM list covers risks introduced by the model layer: instruction manipulation, output that cannot be trusted, excessive agency, and retrieval weaknesses. Use both, not one instead of the other.

Which Entry Should We Address First?

Usually LLM06, excessive agency, and LLM05, improper output handling. Both are architectural, both are entirely within your control, and both determine how much damage every other entry can cause. Prompt injection gets more attention, but an injected prompt against a tightly scoped agent with validated output is an inconvenience rather than an incident.

Is There a Certification Against the List?

No. It is an awareness and prioritisation resource maintained by a community project, not a standard with a conformity scheme. You can require coverage of it in a penetration test scope or a supplier questionnaire, and reference it in your risk documentation, but nobody certifies compliance with it.

How Often Is It Updated?

It has been revised roughly annually since 2023, with the 2025 edition introducing system prompt leakage and vector and embedding weaknesses and reworking several others. Given how quickly AI deployment patterns change, check the current version before using it to scope work rather than relying on a copy saved last year.

Related Terms

You May Be Interested In These

What Is Windows Hello for Business?

Cybersecurity Terms

17 November 2026

What Is Windows Hello for Business?

Read More
What Is Agent Hijacking?

Cybersecurity Terms

17 November 2026

What Is Agent Hijacking?

Read More