Google finds attacker AI framework that finds and runs exploitsNew
GTIG and Mandiant say exploit_agent targets n-days and was found with victim data; theft attribution is unproven.
GTIG and Mandiant say exploit_agent targets n-days and was found with victim data; theft attribution is unproven.
An exposed server ran exploit_agent against patched web apps; an FBI alert says ARTEX has hit multiple sectors since August 2026.
An “exploit_agent” pipeline compared patched code, drafted exploits and ran them with no human in the loop, Google says.
GTIG says CAIRN hit US aerospace targets and a PentAGI variant scanned Asian organizations from late August to early October 2026.
GTIG says a Russian-language framework autonomously weaponized patches, then stole data from French media, entertainment, and education sites.
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 908 readers · 1.1K views · 158 reads · all time 202K views