LLM10 · OWASP LLM Top 10

Unbounded Consumption (LLM10)

An LLM service is consumed in ways that drive cost, latency, or availability problems. Includes denial-of-wallet attacks, resource exhaustion, and model-extraction-style heavy querying.

Rank
LLM10 of 10
In the check
Cited by 1 of the 16 questions
LLM01
Prompt Injection
LLM02
Sensitive Information Disclosure
LLM03
Supply Chain
LLM04
Data and Model Poisoning
LLM05
Improper Output Handling
LLM06
Excessive Agency
LLM07
System Prompt Leakage
LLM08
Vector and Embedding Weaknesses
LLM09
Misinformation
LLM10
Unbounded Consumption
Figure 1. The OWASP LLM Top 10, with LLM10 marked.
In practice

What it looks like in practice

Three shapes this risk takes in real deployments.

Example 1

An attacker scripts unlimited free-tier queries that drive vendor cost spikes.

Example 2

A poorly-designed agent recursively calls itself, exhausting tokens.

Example 3

Model-extraction querying that aims to reproduce a competitor's fine-tuned model.

Controls

Controls that close it

These count toward the Runtime dimension of the check.

Rate limiting at user, IP, and tenant level

Cost monitoring and budget alerts

Anomaly detection on query patterns

Authentication on all AI endpoints

Posture Check

Where the check cites it

The AI Posture Check cites OWASP LLM Top 10, including this entry, when placing you at Crawl, Walk, Run or Sprint.

Question the check may askDimensionCitation
Are prompts and outputs logged, and is anyone alerted on unusual use? Runtime OWASP LLM10, NIST AI RMF MANAGE-2.2
Ready when you are

Score yourself against this framework.

Five questions, each citing its source. You get your stage, your place on the chart and the one move that matters next.

  • A few minutes for most people
  • Free, from CWS
  • Your stage, the chart and the next move, by email or live with an engineer