In 45% of all test cases, LLMs introduced vulnerabilities classified within the OWASP Top 10.
In 45% of all test cases, LLMs introduced vulnerabilities classified within the OWASP Top 10. — This cybersecurity statistic was published by Veracode in July 2025. It covers topics including AI code, Gen AI, LLMs, OWASP. The original data appears in 2025 GenAI Code Security Report. For the full methodology and detailed findings, refer to the original report.
Share or Copy this stat
Frequently Asked Questions
What does this statistic say?
In 45% of all test cases, LLMs introduced vulnerabilities classified within the OWASP Top 10. This data was published by Veracode and covers AI code, Gen AI, LLMs, OWASP.
Where does this data come from?
This statistic comes from 2025 GenAI Code Security Report, published by Veracode on July 30, 2025. You can view the original report at https://www.veracode.com/resources/analyst-reports/2025-genai-code-security-report/.
What cybersecurity topics does this cover?
This statistic relates to AI code, Gen AI, LLMs, OWASP. Browse more statistics on AI code or from Veracode.