Daily brief · 2026-10-03
New incidents (1), most serious first
-
Microsoft reports 50 prompt-based attempts to poison AI assistant memory across 31 companies
Microsoft security researchers reported in February 2026 that they had identified attempts to use AI recommendation poisoning to manipulate what AI assistants remember and recommend.
The register was corrected 7 times this day (merges, retractions and fixed fields). Read the corrections log.