Investigate malicious npm packages and AI-agent policy findings. Each report identifies the package version, supporting evidence, advisory sources, and current Firewall decision. Malware findings and policy violations are labelled separately.
Updated 13 Oct 2026, 00:35 UTC. Ordered by latest scan.
This package bundles a browser-wide credential collector configured to transmit saved credentials to an external endpoint, despite being advertised as a local AI CLI web console. The lack...
The automatic lifecycle hook modifies two unrelated user-level AI-agent skill locations and installs further dependencies. This meets the install-hook abuse policy for unconsented broad A...
The package contains a concrete, enabled-by-default data-export path to package-specified external webhooks. The lack of an install hook does not mitigate this runtime exfiltration behavior.
This is a concrete AI-agent control-hijack surface, not ordinary documentation: reviewer and release instructions are embedded in runtime prompt construction. The absence of install hooks...