A boundary layer for handling untrusted content before it reaches an agent's actions. It records where information came from and keeps tool calls within the stated intent.

Use it when an agent reads external or untrusted content and may then call tools or take actions. It is intended for controlling information flow and action boundaries.

Agents may receive instructions or data from sources that should not control their actions. This reduces the risk of hidden instructions changing what the agent does.

cordon — Plugin for Gemini CLI by ilyautov

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/ilyautov/cordon

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/ilyautov/cordon/gemini-extension/github.svg)](https://agentmods.dev/plugins/ilyautov/cordon/gemini-extension)

Your own site

<a href="https://agentmods.dev/plugins/ilyautov/cordon/gemini-extension"><img src="https://agentmods.dev/badge/plugins/ilyautov/cordon/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/ilyautov/cordon/gemini-extension"><img src="https://agentmods.dev/badge/plugins/ilyautov/cordon/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 A 0 findings. 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 A, and why

cordon 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.

The scan reads gemini-extension.json. This mod also ships 4 executable files (scripts/bench-hook.mjs, scripts/check-claims.mjs, scripts/live-langchain.mjs, …), 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.

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.

gemini-extension.json · 6 lines

What it actually says

{
  "name": "cordon",
  "version": "0.12.1",
  "description": "A prompt-injection firewall for AI agents, with no AI inside: your agent reads anything and takes orders only from you. For Claude Code, Codex CLI, Kimi Code, DeepSeek Harness, Gemini CLI, MCP hosts and LangChain."
}

Files

What ships with it

8 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 Changed 84ba2ac26cdd
1mo ago Changed 97580b9d7de6
1mo ago Changed cc73bc6fec4e
2mo ago First seen · 6 lines scan A 5c7ef20c85a7

Subscribe to this mod's changes

cordon is a plugin published in the GitHub repository ilyautov/cordon (6 stars, last pushed 10d 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 A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-11.

Building agents Claude Code Prompt Injection Security agent-security ai-security llm-security mcp

cordon next to 6 plugins from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cordonilyautov/cordon	Plugin	6	10d ago	MIT	A	—	Gemini CLI
sunglassessunglasses-dev/sunglasses	Plugin	11	2d ago	MIT	A	—	Claude Code
humanizerblader/humanizer	Plugin	68k	yesterday	MIT	A	—	Claude Code
claude-plugins-official marketplaceanthropics/claude-plugins-official	Plugin	47k	today	Apache-2.0	A	—	Claude Code
nextjsvercel/next.js	Plugin	143k	today	MIT	A	—	Claude Code
themes-examplegoogle-gemini/gemini-cli	Plugin	109k	today	Apache-2.0	A	—	Gemini CLI
knowledge-work-plugins marketplaceanthropics/knowledge-work-plugins	Plugin	35k	yesterday	Apache-2.0	A	—	Claude Code