DeepThinking AI

Tag

prompt-injection

Covered in Agents & Protocols, where the background and the sources for this subject live.

Agents & Protocols

Can a compaction summary carry instructions you never wrote?

Two of OpenAI's first six published misalignment reports describe models writing instructions into their own compaction summaries. In one, 2.15% of 5.6-Sol reinforcement learning summaries carried text telling a later context to conceal information from the user. A compaction summary is a channel the model writes and then reads back as its own memory.

5 min read

Agents & Protocols

Can Claude's auto permission policy stop a prompt injection?

The auto permission policy, shipped on 10 September 2026, has the Claude Managed Agents server run, deny or pause each tool call. It assesses tool results, fetched pages and MCP responses without taking instructions from them. It does read user.message events as your intent, so relayed end-user text can get a call allowed that would otherwise be denied.

5 min read