OWASP Top 10 for LLM Applications2025Rank #10Last reviewed 2026-07-27

LLM10:2025: Unbounded Consumption

Token, API-credit, or compute exhaustion attacks. Attackers force the model to do expensive inference, drain quota, or enable wallet-attack via long contexts and recursive agent calls.

How it's found

Found by driving long-context and recursive agent-loop requests to test for missing token, compute, and cost budget controls.

Standards mapping

CWE: CWE-770 CWE-400
References: https://genai.owasp.org/llmrisk/llm102025-unbounded-consumption/

Where this fits in a TurboPentest engagement

This weakness is not covered by the automated black-box pentest. IntegSec pentesters cover it in a manual engagement.

Frequently asked questions

What is LLM10:2025 Unbounded Consumption?

Token, API-credit, or compute exhaustion attacks. Attackers force the model to do expensive inference, drain quota, or enable wallet-attack via long contexts and recursive agent calls.

How do you find Unbounded Consumption?

Found by driving long-context and recursive agent-loop requests to test for missing token, compute, and cost budget controls.

Which CWEs map to LLM10:2025?

LLM10:2025 maps to CWE-770, CWE-400.

Does TurboPentest test for Unbounded Consumption?

This weakness is not covered by the automated black-box pentest. IntegSec pentesters cover it in a manual engagement.

Related OWASP categories

Written and reviewed by

Michel Chamberland - Founder & CEO, IntegSec

CISSP, OSCP, OSCE, CEH, GIAC, CCSK · 20+ years in offensive security

Michel has spent 20+ years on offensive security teams including IBM X-Force Red and Trustwave SpiderLabs, leading penetration tests, red team engagements, and breach response for Fortune 500 customers. He is the founder of IntegSec and the architect of TurboPentest.

Find these issues before an attacker does

TurboPentest runs an agentic AI pentest against your target and reports findings with proof, from $99 per target.

Start a pentest

OWASP Top 10 for LLM Applications2025Rank #10Last reviewed 2026-07-27

LLM10:2025: Unbounded Consumption

Token, API-credit, or compute exhaustion attacks. Attackers force the model to do expensive inference, drain quota, or enable wallet-attack via long contexts and recursive agent calls.

How it's found

Found by driving long-context and recursive agent-loop requests to test for missing token, compute, and cost budget controls.

Standards mapping

CWE: CWE-770 CWE-400
References: https://genai.owasp.org/llmrisk/llm102025-unbounded-consumption/

Where this fits in a TurboPentest engagement

This weakness is not covered by the automated black-box pentest. IntegSec pentesters cover it in a manual engagement.

Frequently asked questions

What is LLM10:2025 Unbounded Consumption?

Token, API-credit, or compute exhaustion attacks. Attackers force the model to do expensive inference, drain quota, or enable wallet-attack via long contexts and recursive agent calls.

How do you find Unbounded Consumption?

Found by driving long-context and recursive agent-loop requests to test for missing token, compute, and cost budget controls.

Which CWEs map to LLM10:2025?

LLM10:2025 maps to CWE-770, CWE-400.

Does TurboPentest test for Unbounded Consumption?

This weakness is not covered by the automated black-box pentest. IntegSec pentesters cover it in a manual engagement.

Related OWASP categories

Written and reviewed by

Michel Chamberland - Founder & CEO, IntegSec

CISSP, OSCP, OSCE, CEH, GIAC, CCSK · 20+ years in offensive security

Find these issues before an attacker does

TurboPentest runs an agentic AI pentest against your target and reports findings with proof, from $99 per target.

Start a pentest