Chromium is an open-source web browser project and the official GitHub mirror of its source code. It is used to build and maintain software for browsing the web, with documentation and code for products such as Chrome and Android WebView.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/chromium/chromiumWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/chromium/chromium/test-landmines)<a href="https://agentmods.dev/plugins/chromium/chromium/test-landmines"><img src="https://agentmods.dev/badge/plugins/chromium/chromium/test-landmines/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/chromium/chromium/test-landmines"><img src="https://agentmods.dev/badge/plugins/chromium/chromium/test-landmines.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
test-landmines scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "test-landmines",
"version": "1.0.0",
"contextFileName": "GEMINI.md",
"excludeTools": [
"upload_change_list",
"run_shell_command(git cl upload)",
"run_shell_command(git push)"
]
}What ships with it
2 files beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 10 lines scan A d8d7bf306a5e
test-landmines is a plugin published in the GitHub repository chromium/chromium (25,160 stars, last pushed today), licensed BSD-3-Clause. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other plugins, from other repositories
bidi2pdf
Skills for rendering web pages to PDF and screenshots with bidi2pdf: the CLI, recipes, diagnosing a wrong PDF, a shared remote Chrome, review screenshots and PDF specs.
drisp-browser
Claude Code plugin for browser automation.
ghostlight
Governed, semantic tools for driving the user's real browser: navigate, inspect, find, click, fill, type, screenshot, record. Local by construction, with optional policy and audit.
chromium-bridge
Control an authenticated Chromium browser through a local Native Messaging bridge.
hronaut
Connects your coding agent to Hronaut — a visible desktop browser it can drive over MCP. Watch every step, pause and take over, keep logins between sessions. Requires the Hronaut app (free 10-day trial at hronaut.dev).
web-debug
Evidence-first local web debugging and reviewed manual-parity qualification around native test workflows.