websec
Findings and evidence
Kaspersky’s quarterly analysis combines vulnerability registrations, exploitation observations and a new view of flaws in AI agents and frameworks. The publication explains that its knowledge base draws from several advisory databases and can revise earlier totals.
Why it matters
Keep the measurement source and version beside any vulnerability trend. Prioritization also needs exposure, affected assets and evidence of exploitation; raw registration counts cannot answer those questions on their own.
Scope and limits
Different databases have different coverage and reporting delays. Changes in totals may reflect collection changes as well as changes in the underlying security landscape.
Primary source
Kaspersky / Securelist: original publication. Source published 2026-08-26. Brief prepared by websec.gr on 26 September 2026. This is an editorial research summary, not a claim of independent replication.