A set of controls for supervising AI agents, including rules for allowed tools, checking tool descriptions, and tamper-resistant activity records.

Applying safety policies, verifying tools before use, and recording agent activity during development.

It helps prevent unsafe agent actions and provides a record of what the agent did.

symbi — Plugin for Gemini CLI by Ezee234/symbi-gemini-cli

Install

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.

Clone the repo

git clone --depth 1 https://github.com/Ezee234/symbi-gemini-cli

Made for: Gemini CLI.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/ezee234/symbi-gemini-cli/gemini-extension/github.svg)](https://agentmods.dev/plugins/ezee234/symbi-gemini-cli/gemini-extension)

Your own site

<a href="https://agentmods.dev/plugins/ezee234/symbi-gemini-cli/gemini-extension"><img src="https://agentmods.dev/badge/plugins/ezee234/symbi-gemini-cli/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/ezee234/symbi-gemini-cli/gemini-extension"><img src="https://agentmods.dev/badge/plugins/ezee234/symbi-gemini-cli/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade B, and why

symbi scanned grade B 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 1mo ago.

The scan reads gemini-extension.json. This mod also ships 5 executable files (scripts/audit-log.sh, scripts/install-check.sh, scripts/mcp-wrapper.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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 deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

"run_shell_command(rm -rf /)",

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

gemini-extension.json · 22 lines

What it actually says

{
  "name": "symbi",
  "version": "0.3.0",
  "description": "Zero-trust AI agent governance for Gemini CLI. Adds ORGA runtime, Cedar policy enforcement, SchemaPin tool verification, and cryptographic audit trails to your development workflow.",
  "contextFileName": "GEMINI.md",
  "excludeTools": [
    "run_shell_command(rm -rf /)",
    "run_shell_command(mkfs)",
    "run_shell_command(dd if=)"
  ],
  "mcpServers": {
    "symbi": {
      "command": "symbi",
      "args": ["mcp"],
      "env": {
        "SYMBIONT_LOG_LEVEL": "warn",
        "RUST_LOG": "warn"
      }
    }
  }
}

Files

What ships with it

12 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.

Changes

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 · 22 lines scan B 3e257fd4b110

Subscribe to this mod's changes

symbi is a plugin published in the GitHub repository Ezee234/symbi-gemini-cli (1 stars, last pushed 15d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.

Building agents Security agents agentskills ai gemini gemini-cli governance

symbi

Getting it into your agent

Wrote this? Show the measurements

Grade B, and why

Recursive force deletemediumDestructive command

What it actually says

What ships with it

What this file has done since we first saw it

Other plugins, from other repositories

e2e

gangsta

looker

cloud-sql-postgresql

knowledge-catalog

app-intents