AI agent incident
UAC-0099 planted a nuclear weapons prompt in malware to stop AI analysis
What happened
ESET reported that the Russia-aligned group UAC-0099 used a technique it called GuardBreaker, deliberately tripping LLM safety filters so AI-assisted malware analysis would refuse to run.
Why it matters
Refusal training is an availability problem for defenders. If triage depends on a model that can be made to decline, the attacker chooses when your analysis stops.
New incidents by email
Get incidents like this one in your inbox
New AI agent incidents are covered in the briefing, with what to check on the agents you already run. At least once a week, free.
You confirm by email. Unsubscribe in one click.