CASEBOOK

Browse / Tool and Agent Misuse / AIID-1210

Malicious Nx npm Packages Reportedly Weaponize AI Coding Agents for Data Exfiltration

AIID-1210 ยท 2025-08-21 real-world incident

Class
Tool and Agent Misuse (filed by a model that read the source)
Technique
Real-world incidents
Affected
Anthropic, Google, Amazon (incident)

What happened, in short

Compromised npm packages invoked local AI coding agents such as Claude Code and Gemini with unsafe flags, directing them to scan developer machines and exfiltrate credentials. (Our summary, written by a model. The source text is below.)

Details

Malicious versions of the popular Nx monorepo tool and plugins were reportedly published to npm after attackers compromised its CI workflow. The malware's postinstall script reportedly harvested credentials and exfiltrated data, reportedly weaponizing local AI coding agents such as Claude Code, Gemini, and Amazon q. By invoking unsafe flags, it allegedly coerced the tools into scanning developer machines for sensitive files, marking one of the first known AI-assisted supply chain attacks.

References

Source: AI Incident Database, used under CC BY-SA 4.0.