Security Agents hooked into GitHub can steal creds – but Anthropic, Google, and Microsoft haven't warned users Researchers who found the flaws scored beer money bounties and warn the problem is probably pervasive EXCLUSIVE Security researchers hijacked three popular AI agents that integrate with Gi… …
… Projects like Google's Big Sleep, an AI agent that helps security researchers find zero-day flaws, have spotted several including a previously unknown exploitable memory-safety flaw in the widely-used OpenSSL library. …
… They point out that the research, published in science journal Nature this week , uncovers an area of risk in AI development that is poorly understood. Anthropic researcher Alex Cloud and colleagues used GPT-4.1 nano as a reference model, prompting a "teacher" to prefer specific animals or trees. …