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/kenryu42/gemini-safety-netWrote 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/kenryu42/gemini-safety-net/gemini-extension)<a href="https://agentmods.dev/plugins/kenryu42/gemini-safety-net/gemini-extension"><img src="https://agentmods.dev/badge/plugins/kenryu42/gemini-safety-net/gemini-extension/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/kenryu42/gemini-safety-net/gemini-extension"><img src="https://agentmods.dev/badge/plugins/kenryu42/gemini-safety-net/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade C, and why
gemini-safety-net scanned grade C with 1 finding 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 16d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"rm -rf", What it actually says
{
"name": "gemini-safety-net",
"displayName": "Gemini Safety Net - Blocks destructive git and filesystem commands",
"version": "2.0.0",
"hooks": "./hooks/hooks.json",
"author": "J Liew",
"license": "MIT",
"repository": {
"type": "git",
"url": "https://github.com/kenryu42/gemini-safety-net.git"
},
"homepage": "https://github.com/kenryu42/gemini-safety-net",
"keywords": [
"gemini",
"rm -rf",
"git",
"safety net",
"destructive",
"command",
"guard",
"hook",
"plugin",
"extension"
],
"dependencies": {
"node": ">=18.0.0"
}
}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.
- 16d ago First seen · 28 lines scan C e14d36d9a477
gemini-safety-net is a plugin published in the GitHub repository kenryu42/gemini-safety-net (2 stars, last pushed 17d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-30.
Other plugins, from other repositories
ccmanager-config
Writes, reviews, and fixes CCManager configuration files (.ccmanager.json and the global config.json): command presets, status/worktree hooks, worktree auto-directory patterns, merge arguments, shortcuts, and auto-approval.
looker
Connect to Looker and interact with your data using LookML.
cloud-sql-postgresql
Create, connect, and interact with a Cloud SQL for PostgreSQL database and data.
knowledge-catalog
Connect to Knowledge Catalog to discover, manage, monitor, and govern data and AI artifacts across your data platform.
firestore-native
Connect and interact with Firestore databases, collections, and documents.
alloydb
Create, connect, and interact with an AlloyDB for PostgreSQL database and data.