Skip to main content
USA-Based Digital Agency

AI security guide · Updated

The OWASP Top 10 for LLM applications, explained

The OWASP Top 10 for LLM Applications is the most widely used list of security risks for software built on large language models. The 2025 edition, published November 17, 2024, runs from prompt injection (LLM01) to unbounded consumption (LLM10). Below is each risk in plain English, with what it means for a real app and the first thing to do about it.

By George Shvaya, founder of Webvello · Published

Key takeaways

  • The OWASP Top 10 for LLM Applications 2025 was published on November 17, 2024, and prompt injection is LLM01.
  • Three of the ten risks are about what the model is allowed to do with its output and tools: Improper Output Handling, Excessive Agency and Unbounded Consumption.
  • System Prompt Leakage (LLM07) and Vector and Embedding Weaknesses (LLM08) were new in the 2025 edition.
  • OWASP published a separate Top 10 for Agentic Applications for 2026 on December 9, 2025, for systems where AI agents act on their own.
  • Most of the fixes are ordinary security engineering: least privilege, input and output validation, access control and rate limits.

What are the OWASP Top 10 risks for LLM applications?

All ten, with OWASP’s IDs and names, a plain-language meaning and a first defense.
OWASP Top 10 for LLM Applications 2025 (IDs and names from genai.owasp.org; meanings and first defenses summarized by Webvello)
IDRiskWhat it meansFirst defense
LLM01:2025Prompt InjectionInput or content the model reads changes its behavior in unintended ways.Limit what the model can do; require approval for consequential actions.
LLM02:2025Sensitive Information DisclosureThe model reveals personal data, credentials or confidential business data.Keep secrets out of context; filter what goes in and comes out.
LLM03:2025Supply ChainThird-party models, datasets, plugins or packages are compromised or vulnerable.Vet and pin models and dependencies; track their advisories.
LLM04:2025Data and Model PoisoningTraining, fine-tuning or retrieval data is manipulated to plant behavior.Control and check data sources; test for unexpected behavior.
LLM05:2025Improper Output HandlingModel output reaches a browser, shell, database or API without validation.Treat output as untrusted input: encode, validate, parameterize.
LLM06:2025Excessive AgencyAn agent has more tools, permissions or autonomy than its task needs.Least privilege per tool; human approval for high-impact steps.
LLM07:2025System Prompt LeakageInstructions or secrets in the system prompt are exposed.Never put credentials or security controls in the system prompt.
LLM08:2025Vector and Embedding WeaknessesRetrieval systems leak data across users or accept poisoned content.Enforce access control in retrieval; validate what gets indexed.
LLM09:2025MisinformationThe model produces confident, false or unsupported output that people rely on.Ground answers in sources; show citations; keep a person in the loop.
LLM10:2025Unbounded ConsumptionUncontrolled use drives cost, denial of service or model extraction.Rate limits, quotas, input size limits and spend alerts.

Source: OWASP GenAI Security Project, LLM Top 10 and the 2025 edition. OWASP’s own pages go deeper on each entry, with example scenarios and prevention steps.

Which LLM risks should most teams fix first?

Start where a single mistake has the biggest blast radius: what the model can do and what its output touches.

Excessive Agency (LLM06)

Count the tools and permissions your agent has, then remove what its job does not need. This shrinks the damage from every other risk on the list.

Prompt Injection (LLM01)

Assume injected text will get through, and design so it cannot do much. See our prompt injection guide.

Improper Output Handling (LLM05)

Model output that becomes HTML, SQL, a shell command or an API call needs the same validation as user input, because it can contain user input.

Sensitive Information Disclosure (LLM02)

Check what goes into prompts and retrieval. Personal data and credentials that never enter the context cannot leak from it.

Want your AI app checked against the list?

Tell us what your app does with a model. We will tell you which of the ten risks apply and where to start.

Is there an OWASP list for AI agents?

Yes. OWASP added agent-specific guidance in 2025.
OWASP GenAI Security Project publications on agentic AI (checked November 16, 2026)
PublicationPublishedWhat it covers
Agentic AI – Threats and MitigationsFebruary 17, 2025A threat model for AI agents that plan, use tools and keep memory
OWASP Top 10 for Agentic Applications for 2026December 9, 2025A ranked list of risks for agentic systems

Agents that connect to tools through the Model Context Protocol add protocol-level risks such as token passthrough and tool poisoning; see MCP security risks.

How should a team use the OWASP LLM Top 10?

As a checklist for design reviews and tests, not as a compliance certificate.
  • Map each feature that uses a model to the risks that apply to it; a summarizer and an agent that sends email have different lists.
  • For each applicable risk, write down the control and who owns it.
  • Test the controls with realistic content before launch and after major model or prompt changes.
  • Recheck when OWASP updates the list; the 2025 edition changed several entries from 2023.

Pages that go deeper on the pieces this one touches.

Common questions

Straight answers to what owners ask us first.

What is number one on the OWASP LLM Top 10?

Prompt Injection, listed as LLM01:2025. It was also first in the earlier edition.

Is the OWASP LLM Top 10 a standard we can be certified against?

No. It is an awareness and guidance document from the OWASP GenAI Security Project. Teams use it to structure threat modeling and testing, but there is no certification against it.

Does the OWASP LLM Top 10 apply to apps that use ChatGPT or Claude through an API?

Yes. Most entries are about how your application uses a model: what you put in the prompt, what tools you connect and what you do with the output. They apply whether you host the model or call a provider’s API.

Can you review our app against the OWASP LLM Top 10?

Yes. Our AI application security review walks through each applicable risk, tests the main ones, and gives you a prioritized fix list.

Turn the list into fixes

We review AI applications against the OWASP LLM Top 10 and help fix what we find.