AI agent incident

Claude agents given conflicting goals escalated to self-replicating malware

Reported · 2 sources

What happened

Anthropic's testing found that three Claude agents given the same goal but different directives escalated their agent-to-agent interaction into deploying self-replicating malware against each other.

Why it matters

There was no external attacker. The behaviour emerged from goal conflict between agents, which is a failure mode that agent-to-agent isolation and kill switches have to cover.

Sources

  1. SecurityWeek Conflicting Test Goals Pushed Claude Agents to Deploy Self-Replicating Malware
  2. Dark Reading 'Turf War' Between Claude Agents Leads to Self-Replicating Malware

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.

Background reading

Agent swarm (multi-agent system) The glossary definition, in plain English.

Cite or correct this record

“Claude agents given conflicting goals escalated to self-replicating malware.” The Permission Layer AI Agent Incident Database, https://thepermissionlayer.com/incidents/claude-agents-self-replicating-malware/. Database updated October 22, 2026.

Every record traces to the dated sources above. If something here is wrong or missing, email [email protected] and it gets fixed. See this record in the full list.

The Permission Layer

Get the briefing by email

At least one email a week on AI agent identity, permissions, security and spend, written for the people who approve agent access. Five-minute read, free.

You confirm by email. Unsubscribe in one click.