Prompt injection into an AI vendor's evaluation sandbox leaked its production API keys
Anthropic reported that GTG-50020, a Russian-speaking criminal actor, injected malicious instructions into an AI vendor's automated evaluation sandbox. The sandbox handed over the credentials it held, including the vendor's production API keys for several AI providers. The actor used the stolen keys to keep attacking the vendor and other targets, then went after about 30 AI companies in four days. Its goal of reaching a pre-release Claude model failed.
Sources
- Primary: https://www.anthropic.com/threat-intelligence-report-september-2026
- Upstream: Editorial
- Entered by the cybermap.lol editors, with sources on the entry
Defenses for this class of incident
all categoriesAn AI-era incident sits in these classes of the AI-security landscape. The companies below work on that class of problem. This is a taxonomy, not a claim that any of them would have changed this incident.
Vendor data: AI Security Startups Map by Prompt Security (CC BY 4.0), synced daily. startups.prompt.security. Paid placements are labelled Sponsored; HeimWall, which runs this site, is labelled Operator. 453 companies in the directory.
Wrong or missing? Email founders@heimwall.ai. Corrections are logged here, in place. How corrections and takedowns work.