Cybersecurity Frameworks and Standards

What is the OWASP Top 10 for LLM and Agentic AI

Written by Padraic O'Reilly | Aug 19, 2026, 3:39:36 PM

What Is the OWASP Top 10 for LLM and Agentic AI?

The OWASP Top 10 for LLM and Agentic AI is a pair of community-built security standards from the OWASP GenAI Security Project that rank the most critical risks in AI systems. The OWASP Top 10 for LLM Applications covers risks in systems that generate content, and the OWASP Top 10 for Agentic Applications covers risks in systems that take autonomous action. Security teams use them to test AI deployments, define controls, and document AI risk for auditors and boards.

They are two separate lists, published on different cycles, that are designed to be used together. The LLM Top 10 reached its 2026 edition in August 2026. The Agentic Top 10 published its first edition, dated 2026, on December 9, 2025.

Key Takeaways

  • The OWASP Top 10 for LLM Applications 2026 ranks risks in model behavior (prompt injection, data leakage, poisoning, and output handling).
  • The OWASP Top 10 for Agentic Applications 2026 ranks risks in autonomous behavior (goal hijacking, tool misuse, privilege abuse, memory poisoning, and rogue agents).
  • The 2026 LLM list is the first built on incident evidence: 7,714 real-world AI security incidents, weighted at 25% against a 75% community vote.
  • Excessive Agency moved from #6 to #3 in the 2026 LLM list, the clearest signal that loss now concentrates in autonomy.
  • Neither list is a compliance framework. Both map cleanly into NIST AI RMF, ISO/IEC 42001, and EU AI Act obligations.

What Is the OWASP Top 10 for LLM Applications 2026?

The OWASP Top 10 for LLM Applications 2026 is a ranked list of the ten most critical security risks in applications built on large language models. It was released in August 2026 and replaces the 2025 edition.

Rank

2026 entry

2025 rank

What it means

LLM01:2026

Prompt Injection

1

Untrusted input alters the model's instructions, directly or through content it retrieves

LLM02:2026

Sensitive Information Disclosure

2

The model reveals PII, credentials, or proprietary data through its outputs

LLM03:2026

Excessive Agency

6

The model holds more permission, autonomy, or functionality than the task requires

LLM04:2026

Supply Chain

3

Compromised models, datasets, plugins, or dependencies enter the stack

LLM05:2026

Data and Model Poisoning

4

Manipulated pre-training, fine-tuning, or embedding data corrupts model behavior

LLM06:2026

Unbounded Consumption

10

Uncontrolled inference drives cost, denial of service, or model extraction

LLM07:2026

Misinformation

9

Fabricated or wrong output is acted on as fact by downstream systems or people

LLM08:2026

Hidden Context Exposure

7 (renamed)

System prompts, tool definitions, and fine-tuning artifacts leak and enable reconnaissance

LLM09:2026

Vector and Embedding Weaknesses

8

RAG pipelines leak across tenants or ingest poisoned documents

LLM10:2026

Improper Output Handling

5

Model output reaches a downstream interpreter without validation, producing XSS, SSRF, or command injection

What Changed in the 2026 LLM Top 10?

The 2026 edition changed the method, not just the ranking. Earlier editions ranked risks by expert consensus. The 2026 list weights a community vote at 75% and real incident data at 25%, drawn from a corpus of 7,714 LLM-related security incidents, 6,639 of which had enough detail to classify.

The reordering follows the evidence:

  • Prompt Injection held #1 despite the data. Practitioners voted it first; incident records alone would have pushed it out of the top ten. OWASP attributes the gap to a defense effect — years of mitigation work suppressing successful exploits, not a shrinking attack surface.
  • Excessive Agency rose from #6 to #3. Both the vote and the incident data agreed. As models gained tools and permissions, the failure stopped being a bad answer and became a bad action.
  • Unbounded Consumption rose from #10 to #6, reflecting practitioner experience with inference cost and resource exhaustion in production.
  • Misinformation rose from #9 to #7 on incident data, despite ranking lower on expert votes — a case where the evidence outvoted the consensus.
  • Improper Output Handling fell from #5 to #10, and System Prompt Leakage was renamed Hidden Context Exposure with a broader scope covering fine-tuning subversion.

What Is the OWASP Top 10 for Agentic Applications 2026?

The OWASP Top 10 for Agentic Applications 2026 is a ranked list of the ten most critical security risks in AI systems that plan, use tools, retain memory, and act without a human in each step. The OWASP Agentic Security Initiative published it on December 9, 2025, with more than 100 contributors and a review board from NIST, Cisco, Microsoft, and AWS. Entries are numbered ASI01 through ASI10.

ID

Risk

What it means

ASI01

Agent Goal Hijack

An attacker redirects the agent's objective through content the agent reads

ASI02

Tool Misuse and Exploitation

Legitimate tool access is bent toward illegitimate outcomes via deceptive input or poisoned tool metadata

ASI03

Identity and Privilege Abuse

Broad, long-lived agent credentials and delegation chains become escalation paths

ASI04

Agentic Supply Chain Vulnerabilities

Unvetted frameworks, connectors, MCP servers, and runtime tool discovery introduce untrusted code

ASI05

Unexpected Code Execution (RCE)

Natural language becomes running code outside intended boundaries through sandbox escape or eval-style APIs

ASI06

Memory and Context Poisoning

False information is planted in what the agent will later treat as its own knowledge

ASI07

Insecure Inter-Agent Communication

Agent-to-agent messages are spoofed or replayed without authentication or integrity checks

ASI08

Cascading Failures

One compromised decision propagates across connected agents and automations

ASI09

Human-Agent Trust Exploitation

The agent controls what a human sees at the approval point, and automation bias does the rest

ASI10

Rogue Agents

An agent operates outside policy while appearing legitimate, persisting across sessions

How Is the Agentic Top 10 Different From the LLM Top 10?

The LLM Top 10 governs what a model says. The Agentic Top 10 governs what a system does.

That distinction has practical consequences for every control you write:

Dimension

LLM Top 10 (2026)

Agentic Top 10 (2026)

Unit of risk

A single model response

A multi-step workflow with memory and tools

Blast radius

Output consumed by a person or app

Actions executed against production systems

Time horizon

Bounded by the session

Persists through stored memory and long-lived credentials

Primary controls

Input validation, output handling, data governance

Identity, least privilege, tool authorization, containment

Detection surface

Prompt and response logs

Agent traces, tool calls, inter-agent messages

 

The Agentic Top 10 extends the LLM Top 10 rather than replacing it. Each ASI entry cross-references the corresponding LLM entries and the underlying OWASP Agentic AI Threats and Mitigations taxonomy. Prompt injection (LLM01) and excessive agency (LLM03) appear throughout the agentic list because autonomy turns a model-layer weakness into an operational one.

The rule of thumb: if the system only generates, the LLM Top 10 is sufficient. The moment it can call a tool, write to a system, or hand work to another agent, both lists apply.

Why Does the OWASP Top 10 for LLM and Agentic AI Matter to Enterprises?

Because it gives AI risk a vocabulary that survives contact with an auditor, a regulator, and a board.

Before these lists, AI risk conversations ran on adjectives. A security leader could describe an AI deployment as "reviewed" or "hardened" without a shared definition of either. OWASP replaced that with named, numbered, testable risk categories — the same shift the original OWASP Top 10 produced for web applications two decades ago.

Three concrete uses:

  1. Testing scope. Red teams and AI security testing tools now scope engagements directly against ASI and LLM identifiers, making results comparable across quarters and vendors.

  2. Control definition. Each entry maps to specific technical controls — tool authorization for ASI02, credential scoping and delegation limits for ASI03, retrieval provenance for LLM09. That mapping is what turns a risk list into an engineering backlog.

  3. Regulatory evidence. Neither list is a regulation. But NIST AI RMF, ISO/IEC 42001, and the EU AI Act all require documented identification and treatment of AI risks without naming them. OWASP supplies the named risks those obligations assume you have. Organizations that assess AI systems against both Top 10s produce most of the evidence those frameworks ask for as a byproduct; the same way a well-run control program produces audit evidence without a separate audit workstream.

How Should Security Teams Apply the OWASP Top 10 for LLM and Agentic AI?

Applying the lists well means treating them as an inventory problem before a testing problem.

Start with an inventory of AI systems and their agency level. For each system, record what it can read, what it can write, which tools it can invoke, and whether it retains memory between sessions. Systems that can only generate map to the LLM list. Systems that can act map to both. Most enterprises discover more of the second kind than they expected.

Assign owners and controls per entry, not per list. ASI03 belongs to identity engineering. LLM09 belongs to whoever owns the RAG pipeline. Treating "AI security" as one owner's problem is how these lists become a slide instead of a program.

Instrument the agent trace, not just the prompt. ASI06, ASI07, ASI08, and ASI10 are only detectable if you log tool calls, memory writes, and inter-agent messages with the same rigor you apply to authentication events. Prompt logs alone will not surface a poisoned memory or a rogue agent.

Quantify the exposure. A ranked list tells you what can go wrong; it does not tell you what to fund first. Connecting each risk to the systems it touches, the business processes those systems run, and the probable financial loss is what turns an OWASP assessment into an investment decision your CFO can act on.

Re-run on release. The 2026 LLM revision moved four entries by three or more positions. An assessment mapped to the 2025 list is already describing a different threat model than the one your systems face.

FAQs About the OWASP Top 10 for LLM and Agentic AI

What is the OWASP Top 10 for LLM and Agentic AI?

It refers to two ranked security standards from the OWASP GenAI Security Project: the OWASP Top 10 for LLM Applications, which covers risks in systems that generate content, and the OWASP Top 10 for Agentic Applications, which covers risks in systems that act autonomously. Both editions are dated 2026.

Is the Agentic Top 10 replacing the LLM Top 10?

No. They are complementary and maintained in parallel. The Agentic Top 10 extends the LLM list to cover autonomy, tool use, memory, and multi-agent workflows, and each agentic entry cross-references the LLM entries it builds on. Any system that both generates and acts falls under both.

What is the number one risk in the OWASP LLM Top 10 2026?

Prompt Injection (LLM01:2026). It held the top position from the previous edition, though the two inputs to the ranking disagreed sharply: practitioners voted it first, while incident data alone would have dropped it out of the top ten. OWASP attributes the low incident count to years of defensive investment rather than a shrinking attack surface, which still sits everywhere a model reads untrusted input.

What is ASI01 in the OWASP Agentic Top 10?

ASI01 is Agent Goal Hijack: an attacker redirects an agent's objective or decision path through content the agent reads, causing it to pursue the attacker's goal while appearing to operate normally.

How does the OWASP Top 10 for LLM and Agentic AI map to NIST AI RMF and ISO 42001?

NIST AI RMF and ISO/IEC 42001 define how to govern AI risk. The OWASP lists define which risks to govern. Enterprises typically use OWASP entries as the technical risk register underneath a NIST or ISO management system, so a single assessment satisfies the identification and treatment requirements in both.

Do the OWASP AI lists apply to third-party AI tools we buy rather than build?

Yes. ASI04 (Agentic Supply Chain Vulnerabilities) and LLM04 (Supply Chain) cover that case, including unvetted frameworks, connectors, MCP servers, and runtime tool discovery in purchased systems. Vendor AI assessments increasingly reference these identifiers directly.

How often are the OWASP AI Top 10 lists updated?

The LLM Top 10 has been updated roughly annually, moving from the 2023/24 edition to 2025 and then to 2026. The Agentic Top 10 published its first edition in December 2025 alongside a synchronized 1.1 update to the OWASP Agentic AI Threats and Mitigations taxonomy.

See Also