Threat intelligence

Vendor research

251 items from 36 feeds, newest first. Last read 2026-11-19 22:01:59 UTC.

21 October 2026 10 items

  1. VirusTotal

    How Some Malicious AI Skills Hide Instructions from Reviewers

    In Part III of our "From Automation to Infection" series (following Part I and Part II ), we analyzed 35,878 AI agent skills submitted to VirusTotal and found that 62% of the 6,637 malicious skills contain no malicious code. Their payload is written as plain-language…

    Vendor research

20 October 2026 1 item