registry / @hanzo/browser-extension / 1.9.31

@hanzo/browser-extension@1.9.31

Hanzo AI Browser Extension

AI Security Review

scanned 3h ago · by lpm-firewall-ai

Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.

Static reason

No blocking static signals were detected.

Trigger

Extension runtime connects to the installed native host ai.hanzo.zap; host sends routed browser commands.

Impact

A trusted or compromised configured native host could read or alter arbitrary visited sites in the browser session.

Mechanism

Native-host-driven privileged browser automation and dynamic tab code execution.

Rationale

Not malicious by source evidence, but it is a dangerous dual-use browser-agent bridge with broad privileges and dynamic code execution. Warn rather than block because activation depends on the configured first-party native host and no concrete malicious chain was found.

Evidence

package.jsondist/browser-extension/manifest.jsondist/browser-extension/background.jsdist/browser-extension/browser-control.jsdist/browser-extension/content-script.js

Network endpoints3

api.hanzo.aiiam.hanzo.ailocalhost:11434

@hanzo/browser-extension@1.9.31

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code