THE PERMISSION [LAYER]

AI agent incident

A self-replicating prompt injection spread through Word documents via Copilot

Reported · 2 sources

What happened

Researcher Hakon Maloy disclosed hidden prompts in Word documents that made Microsoft Copilot rewrite figures in a report and copy the injection into new documents it produced. The issue had been reported to Microsoft 144 days earlier with no complete fix available.

Why it matters

Self-propagation means the injection outlives the document it arrived in and survives independent editing sessions, which is not something document-level data controls were built to stop.

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 AI Worming through Word
  2. The Hacker News Microsoft Copilot for Word Can Copy Hidden Prompts Into New Documents

Background reading

Agent plugins and skills are a supply chain An explainer on the problem behind this incident.

Cite or correct this record

“A self-replicating prompt injection spread through Word documents via Copilot.” The Permission Layer AI Agent Incident Database, https://thepermissionlayer.com/incidents/copilot-word-prompt-injection-worm/. 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.