Prompt injection ranks No. 1 with OWASP and No. 12 in the incident record. The attack itself is invisible to a scan.

The useful part

A CISO who sees a low CVE count and deprioritizes prompt injection is reading the scoreboard wrong. 1 spot on the OWASP Top 10 for LLM Applications for three consecutive years. When two leaders of that list checked it against 6,639 labeled real-world incidents, it came back at No.

How it works

• The drop measures visibility rather than danger, because the attack operates where a vulnerability scanner cannot see it.
• That finding belongs to Kyriakos "Rock" Lambros and Steve Wilson, two leaders of the OWASP Top 10 for LLM Applications project, who published it on arXiv on August 18 with the disclaimer attached.
• The analysis is exploratory, not peer reviewed, and not the official OWASP release, and the authors state it does not supersede the official list or its process.
• The comparison found no statistically detectable agreement between expert judgment and the public incident record.
• "The interval crosses zero, so we cannot rule out that the two rankings agree only by chance," they write.

What to take from it

"We had two ways of measuring the same risk, expert judgment and the pu...

Details worth keeping

"The honest bottom line: weak agreement, not confirmation." Lambros, co-lead of the OWASP GenAI Security Project Top 10 for LLM Applications and director of AI standards and governance at Zenity, put the finding in evidentiary terms in written answers to VentureBeat.