Google says attackers now run autonomous AI exploit agents
GTIG found an exposed multi-agent framework that drafts and runs exploits, plus resale of stolen model access.
76
GTIG found an exposed multi-agent framework that drafts and runs exploits, plus resale of stolen model access.
CAIRN and PentAGI were used in real attacks, including against US aerospace, while exploit_agent built and ran exploits with no human in the loop.
An exposed exploit_agent compared code before and after patches and ran exploits; configuration notes were in Russian.
GTIG says exploit_agent ran without a human and projects low-interaction attacks within three months.
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.
Today 902 readers · 1.1K views · 158 reads · all time 202K views