Skip to the content
AI and Cybersecurity Learning and Practice Center Test automation Open the Learning Center

WeaknessASC-2026-0027Other weakness

Self-replicating prompt injection (AI worms)

MediumWorkarounds only

Injected text that tells an agent to copy it into its own outputs (emails, files, comments) spreads to every agent that reads those outputs next.

How to detect it

  • Outgoing messages or files that contain instructions copied from incoming content
  • The same unusual text appearing across many agent outputs

Workarounds

  • Scan agent outputs as well as inputs for instruction-like text
  • Require approval before agents send messages or write shared files
  • Rate limit agent-generated outbound messages

Demonstrated in research (the Morris II worm, 2024), in 2026 against Copilot in Word, where hidden text copied itself into each new document, and by OpenAI's red-teaming models, which wrote injections that spread through email, files and Slack in internal research checkpoints (disclosed September 2026); defenses are the same as for prompt injection.

How to investigate

  1. Trace the first message that carried the text and every agent output that copied it
  2. Quarantine affected mailboxes, channels or files

Sources

Open it in the Learning Center's vulnerability database