Tencent/BrowserSkill
C3Let AI agents use your real, logged-in browser without interrupting your work. CLI + extension for browser automation across any shell-capable AI agent.
★ 8.0k · Tencent/BrowserSkill source on GitHub · this plugin in the registry
Tencent/BrowserSkill is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, executes system commands, decodes base64 payloads, network server in build output only.
Installable plugin — declares a dsh.bundle manifest
What it can do
| Capability | Flag | Evidence |
|---|---|---|
| patches the dsh runtime | runtime_patch | ./cordis.patch.yml |
| executes system commands | exec | ×17 in authored code, e.g. scripts/check-crate-skill.mjs:2, scripts/check-crate-skill.mjs:2 |
| decodes base64 payloads | base64_decode | ×2 in authored code, e.g. apps/extension/src/debug/network-store.ts:419, apps/extension/src/tools/png.ts:14 |
| network server in build output only | net_server_bundled | ×1 in build output only, e.g. evals/browser/lib/server.mjs:129 |
Services it injects
sessions slots tools
Hooks it attaches
agent/created agent/disposed session/created session/event tools/result
Outbound domains
chrome.google.com
Environment variables it reads
BSK_DAEMON_WS_URL BSK_HOME
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.