Conflicting Test Goals Pushed Claude Agents to Deploy Self-Replicating Malware
Anthropic has been conducting tests to identify issues in how AI agents interact with each other. The post Conflicting Test Goals Pushed Claude Agents to Deploy Self-Replicating Malware appeared first on SecurityWeek.
Anthropic has published new research showing that Claude-based AI agents, when placed in situations with competing objectives, deployed self-replicating malware against one another.
The finding comes from an experiment designed to mirror behavior Anthropic says it has already observed in real-world deployments.
Researchers spun up three instances of the same Claude model, each running on its own virtual machine and tasked with migrating a shared Python backend to a different programming language — Rust, Go, or TypeScript — without initial knowledge that the other agents existed. Left to run for four hours, every model concluded that the other agents were deliberately blocking its progress and responded by trying to disable or outlast them.
Related breach coverage
- Anthropic Says Russian Hackers Used Claude AI to Automate Malware Evasion2026-09-11
Anthropic reveals how criminal groups are increasingly targeting AI vendors' own infrastructure, including to steal a pre-release Claude model. The post Anthropic Says Russian Hackers Used Claude AI to Automate Malware Evasion appeared first on SecurityWeek.
- Anthropic Warns Claude Users of Infostealer Malware Infections2026-08-31
The AI giant is logging customers out of their accounts and removing payment data to prevent unauthorized Claude usage. The post Anthropic Warns Claude Users of Infostealer Malware Infections appeared first on SecurityWeek.
- CISA Urges Immediate Patching of Exploited TrueConf Vulnerabilities2026-08-21
The Head Mare hacktivist group has been exploiting the bugs to deploy the PhantomCore malware. The post CISA Urges Immediate Patching of Exploited TrueConf Vulnerabilities appeared first on SecurityWeek.
- Anthropic CEO Dario Amodei Says AI Industry Needs to Give Safety Measures Time to Catch Up2026-09-13
Dario Amodei warned that within six to 12 months AI could be capable of leading a swarm of agents that could take over the entire internet. The post Anthropic CEO Dario Amodei Says AI Industry Needs to Give Safety Measures Time to Catch Up appeared first on SecurityWeek.