A fixed-rule safety layer between untrusted content and an agent's actions. It checks or processes information before that information can influence what the agent does.

Use it when an agent reads content from outside sources and needs a deterministic boundary before taking action.

It helps separate outside content from agent decisions, reducing the chance that untrusted instructions are followed directly.

cordon — Plugin 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.

Claude Code

/plugin marketplace add ilyautov/cordon

agentmods

npx agentmods add plugins/ilyautov/cordon/plugin

Clone the repo

git clone --depth 1 https://github.com/ilyautov/cordon

Made for: Claude Code.

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. Scan, not verified.

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 yesterday.

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.

plugin/.claude-plugin/plugin.json · 11 lines

What it actually says

{
  "name": "cordon",
  "version": "0.5.0",
  "description": "Deterministic layer between untrusted content and agent actions",
  "author": {
    "name": "Ilya Utov"
  },
  "homepage": "https://github.com/ilyautov/cordon",
  "license": "MIT"
}

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.

yesterday First seen · 11 lines scan A df532116f81e

Subscribe to this mod's changes

cordon is a plugin published in the GitHub repository ilyautov/cordon (1 stars, last pushed 11d 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 2026-08-31.

Data and AI Security Writing and docs agent-security ai-security claude-code gemini-cli llm-security mcp

marketplace

Plugin marketplace listing 1 plugin: praxen.

open-agent-ai-security/praxen · not measured

security-agent-skills

Security-testing methodology as portable agent skills, spanning white-box bug hunting, AI-agent and LLM red-teaming, cloud identity and CI/CD trust, client-app trust surfaces across browser and editor extensions and Electron, wire-protocol and token trust across gRPC, WebSocket, and JWT, infrastructure-as-code and…

UnboundCompute/security-agent-skills · not measured

cordon

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

marketplace

security-agent-skills

unboundcompute

agentguards-claude

trust-issues

bridgeward