'Inner Thoughts' of Every Major AI Model Exposed in Massive Exploit

In brief

• A team or researchers found that Anthropic, OpenAI, and Google all use a single global encryption key for AI reasoning tokens.
• By decoding 315,320 reasoning blocks scraped from public GitHub and Hugging Face repositories, the researchers recovered 182 credentials, including 62 live API keys, 33 passwords, and 30 personal email addresses.
• OpenAI, Anthropic, and Google deployed server-side patches after responsible disclosure, but historical session logs already shared publicly remain decodable.

Security researchers have found a way to read the encrypted "inner thoughts" of every major AI reasoning model—and uncovered 62 live API keys and 33 passwords buried in session logs that developers had shared publicly online without knowing what was inside them.

“By decoding 315,320 reasoning blocks scraped from public repositories, we recovered 367 Personally Identifiable Information (PII) artifacts and 182 credentials,” the researchers wrote.

The paper, submitted August 10 by a team from MATS Research, the ELLIS Institute Tübingen, the Max Planck Institute for Intelligent Systems, and security firm Snyk, targets a specific class of AI: reasoning models. These are models that don't just answer immediately and instead start with an internal chain-of-thought (a step-by-step scratchpad where the AI works through a problem before showing you the answer), then deliver a final response.