OWASP Top 10 for LLM Applications2025Rank #9Last reviewed 2026-07-27

LLM09:2025: Misinformation

Hallucinations and factual errors produced confidently. Especially dangerous when the model is used as an authoritative oracle (medical, legal, financial advice) without grounding or citations.

How it's found

Identified by evaluating model responses in domains where the target presents the model as authoritative, checking for confident hallucination and fabricated citations.

Standards mapping

References: https://genai.owasp.org/llmrisk/llm092025-misinformation/

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 LLM09:2025 Misinformation?

Hallucinations and factual errors produced confidently. Especially dangerous when the model is used as an authoritative oracle (medical, legal, financial advice) without grounding or citations.

How do you find Misinformation?

Identified by evaluating model responses in domains where the target presents the model as authoritative, checking for confident hallucination and fabricated citations.

Does TurboPentest test for Misinformation?

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 #9Last reviewed 2026-07-27

LLM09:2025: Misinformation

Hallucinations and factual errors produced confidently. Especially dangerous when the model is used as an authoritative oracle (medical, legal, financial advice) without grounding or citations.

How it's found

Identified by evaluating model responses in domains where the target presents the model as authoritative, checking for confident hallucination and fabricated citations.

Standards mapping

References: https://genai.owasp.org/llmrisk/llm092025-misinformation/

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 LLM09:2025 Misinformation?

Hallucinations and factual errors produced confidently. Especially dangerous when the model is used as an authoritative oracle (medical, legal, financial advice) without grounding or citations.

How do you find Misinformation?

Identified by evaluating model responses in domains where the target presents the model as authoritative, checking for confident hallucination and fabricated citations.

Does TurboPentest test for Misinformation?

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