Vulnerabilities can lurk within production code for years or decades — and AI tools have opened a gateway to a glut of new long-hidden discoveries.

A team of eight researchers reports that encrypted reasoning blocks returned by major AI model APIs can sometimes be replayed to a compatible, less guarded model, which then transcribes the ...

Replayable AI reasoning blocks let researchers recover API keys and passwords from public logs; they say the main extraction attack is now mitigated.

Terabytes worth of credentials, many belonging to the world’s biggest and most sensitive organizations, have been exposed in a supply-chain attack on LiteLLM, an open source tool that streamlines ...