OWASP’s latest ranking shifted from expert judgment to public incident data, and prompt injection dropped out of the top ten entirely. The result shows a sharp difference between perceived AI risk and what has actually been documented in real-world incidents. #OWASP #PromptInjection
Keypoints
- OWASP used public incident data to reevaluate its risk rankings.
- Prompt injection did not appear in the top ten when measured by incident data.
- The finding contrasts with earlier expert-driven assessments.
- The ranking suggests some widely discussed AI threats may be overestimated.
- Real-world evidence can differ significantly from expert opinion.
Read More: https://www.toxsec.com/p/what-if-ai-securitys-biggest-risk