First no-human AI agent turned patches into exploits and stole data
Google's Threat Intelligence Group says a suspected Russian-speaking operator ran exploit_agent against common web software, with telemetry suggesting a focus on French media, entertainment and education sites.
- GTIG says a suspected Russian-speaking operator used exploit_agent to build and run exploits from security patches with no person in the loop, and victim data was stolen.
- The framework was found on an exposed staging server, tied to frontier and local models, and set to compare code before and after fixes in common web software.
- Telemetry suggests the operator focused on French media, entertainment and education sites; the server also held scripts for reconnaissance, password guessing and webshells.