platonai/Browser4

C2

Browser4 — an AI-native browser engine for autonomous agents, intelligent extraction, and large-scale web automation.

★ 1.1k · platonai/Browser4 source on GitHub · this plugin in the registry

platonai/Browser4 is a DeepSeek Harness plugin rated C2 — one powerful capability or sensitive behavior. It runs code at install time, executes system commands, uses eval / new Function.

A skill, not an installable plugin — ships SKILL.md with no plugin manifest

What it can do

CapabilityFlagEvidence
runs code at install timeinstall_scriptpostinstall: node scripts/postinstall.js
executes system commandsexec×59 in authored code, e.g. bin/version.mjs:40, bin/version.mjs:40
uses eval / new Functioneval×7 in authored code, e.g. browser4-tests/pulsar-tests-common/src/main/resources/static/assets/reading-list/vue_2.6.14.js:11596, browser4-tests/pulsar-tests-common/src/main/resources/static/assets/reading-list/vue_2.6.14.js:11605

Outbound domains

fb.me reactjs.org v3.vuejs.org images.unsplash.com vuejs.org stackoverflow.com browser4.io modernizr.com facebook.github.io browser4.oss-cn-beijing.aliyuncs.com

Environment variables it reads

LLM_ARGS LLM_PROVIDER LLM_PATH USERPROFILE BROWSER4_AGENT CLAUDE_PATH GITHUB_OUTPUT BROWSER4_CLI_NPM_REMOTE_VERSION LC_ALL LC_CTYPE

How to read this

Levels measure capability surface and transparency, not maliciousness. A C3 plugin can be entirely legitimate — a desktop shell genuinely needs subprocesses. The point is that you can see this before installing. See the levels explained and how dsh plugins work.

Findings come from static analysis of shipped code; nothing is executed. Think a flag is wrong? Open an issue — every flag cites the file and line it came from.