Executive Summary
A flaw in how OpenAI, Anthropic and Google carried encrypted hidden reasoning between API calls let researchers replay reasoning blocks across sessions and recover internal reasoning and secrets, including API keys and passwords, from session logs.
What Happened
A newly disclosed flaw in the way OpenAI, Anthropic, and Google carried hidden AI reasoning between API calls let researchers recover internal reasoning and secrets from session logs, including API keys and passwords. The weakness affected encrypted reasoning objects used by the providers' reasoning APIs, where a block created in one session could be replayed into another and, during testing,
Affected Products
- OpenAI reasoning API
- Anthropic API
- Google Gemini API
Vulnerability / Attack Technique
Replay of encrypted reasoning objects across sessions
Technical Mechanism
Encrypted reasoning blocks from one session could be replayed into another, where a weaker model could decode them and expose secrets.
AI Security Category
LLM02:2025 Sensitive Information Disclosure
Relevant Frameworks
RealGround Analysis
Secrets that end up in model reasoning can leak through it. RealGround analysis: never put secrets into prompts or tool outputs a model reasons over.
Recommended Controls
- Keep secrets out of prompts and tool results
- Do not store or replay reasoning blocks across sessions
- Rotate any secrets that appeared in reasoning logs
Related RealGround Service
AI Security Readiness Assessment · or start with the free AI Agent Security Scanner.
Sources
thehackernews.com: https://thehackernews.com/2026/08/openai-anthropic-google-api-flaw-let.html
Summary and analysis written by RealGround from the source above; last updated 2026-10-18.