An application-security tool for software that uses AI agents or language models. It creates an AI software bill of materials, checks code, validates behaviour, and performs adversarial tests that try to expose weaknesses.

It is for reviewing AI applications, testing their defenses, and documenting the AI components they contain.

It helps find security problems in AI applications before attackers or unexpected inputs do. An AI software bill of materials is an inventory of the AI components and models an application uses.

nuguard — Plugin for Gemini CLI by NuGuardAI

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/NuGuardAI/nuguard

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/nuguardai/nuguard/gemini-extension/github.svg)](https://agentmods.dev/plugins/nuguardai/nuguard/gemini-extension)

Your own site

<a href="https://agentmods.dev/plugins/nuguardai/nuguard/gemini-extension"><img src="https://agentmods.dev/badge/plugins/nuguardai/nuguard/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/nuguardai/nuguard/gemini-extension"><img src="https://agentmods.dev/badge/plugins/nuguardai/nuguard/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 unknown No closer match found in the catalogue.

Security

Grade A, and why

nuguard 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 13d ago.

The scan reads gemini-extension.json. This mod also ships 8 executable files (scripts/cleanup-codespace.sh, scripts/publish_smithery.py, scripts/push-plugin.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.

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 · 7 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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.

13d ago Changed 24ab3b06667a
16d ago Changed ef60250da2e2
17d ago Changed ba9c38fa7bea
18d ago Changed 51e463e1bd06
19d ago Changed 547d1c30867f
23d ago Changed d9adc3f3b325
1mo ago Changed 109cf619908a
1mo ago Changed 865f480c5aab
1mo ago First seen · 7 lines scan A 10c56c53ffdf

Subscribe to this mod's changes

nuguard is a plugin published in the GitHub repository NuGuardAI/nuguard (64 stars, last pushed today), with no licence file. 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.

Security adversarial-machine-learning agentic-ai ai-agents ai-red-teaming ai-security mcp

aka-claude-tools

AKA Claude Tools guard hooks (command-guard, leak-guard, mcp-guard, post-guard) for your active profile. Requires bun. If bun is missing, the guards fail OPEN (the tool call proceeds) and announce themselves inactive at session start; with bun present, mcp-guard blocks on its own errors. For the full hardened ISOLATED.

akasecurity/claude-tools · not measured

ai-design-engineer

Human-first AI Design Engineer toolkit with 8 specialized personas for resilient agentic systems: Blueprompt (app specs), Brooks (JTBD methodology), Agenisea (multi-agent architecture), Atlas (data & ML architecture), Argus (security), Angel (backend systems), Clarity (human-first UX research & strategy), and Bliss…

agenisea/ai-design-engineering-cc-plugins · not measured

trustshell

AI agent security for Claude Code — read the code, break the running agent, prove it (exploit-validated). Commands: /static-scan, /red-team. Subagent: agent-red-teamer. Skills: RT-1..RT-9.

William2333ZZ/trustshell · not measured

sail

Apply the SAIL V2 (Secure AI Lifecycle) framework by Pillar Security to secure AI applications and agents — gap analyses, security roadmaps, maturity assessments, compliance checklists, control prioritization, and vendor RFPs. Grounded in the full 91-risk SAIL catalog.

pillar-labs/sail-skill · not measured

rudder

Maintain a device-local spec from coding-session intent, then generate focused unit tests with your existing coding agent.

RudderCode/Rudder · not measured

humanizer

Rewrite AI-sounding text so it reads like the writer without changing what it says.

blader/humanizer · not measured