THE PERMISSION [LAYER]

AI agent incident

Encrypted reasoning blocks could be replayed across OpenAI, Anthropic, and Google APIs

Reported · 2 sources

What happened

Researchers replayed encrypted chain-of-thought blocks across sessions on all three providers' APIs to jailbreak weaker sibling models and recover hidden reasoning in plaintext, including secrets such as API keys.

Why it matters

The encrypted reasoning object was trusted by downstream models because it was encrypted, not because anything checked that it belonged to that conversation.

New incidents by email

Get incidents like this one in your inbox

New AI agent incidents are covered in the briefing, with what to check on the agents you already run. At least once a week, free.

You confirm by email. Unsubscribe in one click.

Sources

  1. Simon Willison Stealing Reasoning Traces from Proprietary LLM APIs
  2. The Hacker News OpenAI, Anthropic, Google API Flaw Let Weaker AI Models Decode Stronger Models' Reasoning

Background reading

What is agent identity? An explainer on the problem behind this incident.

Cite or correct this record

“Encrypted reasoning blocks could be replayed across OpenAI, Anthropic, and Google APIs.” The Permission Layer AI Agent Incident Database, https://thepermissionlayer.com/incidents/reasoning-trace-replay/. Database updated November 10, 2026.

Every record traces to the dated sources above. If something here is wrong or missing, email editor@thepermissionlayer.com and it gets fixed. See this record in the full list.

The Permission Layer

Get the next incident like this explained

When an AI agent breaks out, leaks data or runs up a bill, the briefing covers what happened and what to check on the agents you already run. At least once a week, five-minute read, free.

You confirm by email. Unsubscribe in one click.