@prestyj/boss@5.32.0
Orchestrator agent that drives multiple ezcoder sessions across projects from a single chat
AI security review
scanned · by lpm-firewall-aiSource inspection found no concrete attack behavior: the suspicious IP is a radio stream, and the credential-related findings align with the Anthropic API client. The manifest has no install hook, and the flagged helper file is not a declared package entrypoint.