ai-security-tooling

ai-security-tooling is a skill for Claude Code from gmh5225/awesome-ai-security. It costs 29 tokens per session (699 once invoked), scanned A, original, MIT.

A guide for choosing and organizing tools that test and protect AI systems, such as chatbots and machine-learning models. It covers safety checks, attack testing, vulnerability scanning, and security benchmarks.

In plain words
What is it for?
Use it when adding or sorting AI security tools, adversarial machine-learning libraries, red-team tools, benchmarks, or security frameworks in a README.
Why use it?
It helps keep different AI security tools in consistent categories and README sections. This makes a security resource list easier to maintain and use.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Use it when adding or sorting AI security tools, adversarial machine-learning libraries, red-team tools, benchmarks, or security frameworks in a README.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gmh5225/awesome-ai-security/tooling
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.

Any agent
npx skills add gmh5225/awesome-ai-security --skill tooling
Clone the repo
git clone --depth 1 https://github.com/gmh5225/awesome-ai-security

Made for: Claude Code.

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.

agentmods badge for ai-security-tooling

README.md
[![agentmods](https://agentmods.dev/badge/skills/gmh5225/awesome-ai-security/tooling/github.svg)](https://agentmods.dev/skills/gmh5225/awesome-ai-security/tooling)
Your own site
<a href="https://agentmods.dev/skills/gmh5225/awesome-ai-security/tooling"><img src="https://agentmods.dev/badge/skills/gmh5225/awesome-ai-security/tooling/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.

agentmods 80×15 button for ai-security-tooling

Your own site · 80×15
<a href="https://agentmods.dev/skills/gmh5225/awesome-ai-security/tooling"><img src="https://agentmods.dev/badge/skills/gmh5225/awesome-ai-security/tooling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 699 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00029 $0.00699
Opus 5 $0.00015 $0.00349
Sonnet 5 $0.00006 $0.00140
Haiku 4.5 $0.00003 $0.00070

Measured 10d ago against content hash c9d1fdd71270, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ai-security-tooling 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 10d 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.

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.

.claude/skills/tooling/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Security Tooling

Scope

Use this skill when adding or organizing:

  • LLM security tools (guardrails, detectors)
  • Adversarial ML libraries
  • AI vulnerability scanners
  • Model safety tools
  • Security benchmarks and frameworks

Tool Categories

LLM Security Tools

  • Guardrails: NeMo Guardrails, LLM Guard, Rebuff
  • Detectors: Vigil-LLM, Nova Framework, Garak
  • Scanners: ModelScan, AI Security Analyzer

Adversarial ML Libraries

  • Attack libraries: ART, CleverHans, Foolbox, TextAttack
  • Defense libraries: SecML
  • Fuzzing: OSS-Fuzz-Gen, Brainstorm

AI Red Teaming

  • Microsoft: Counterfit, PyRIT
  • Meta: PurpleLlama
  • NVIDIA: Garak, NeMo Guardrails

Benchmarks

  • Robustness: RobustBench
  • Jailbreak: JailbreakBench
  • Safety: Stanford AIR-Bench
  • Hallucination: Vectara Leaderboard

Standards & Frameworks

  • MITRE ATLAS: AI threat matrix
  • NIST AI RMF: Risk management framework
  • OWASP: LLM Top 10, GenAI Security Project

Categorization Rules

  • LLM guardrails/detectorsAI Security & Attacks → Model Security
  • Prompt injection toolsAI Security & Attacks → Prompt Injection
  • Adversarial ML librariesAI Security & Attacks → Adversarial Attacks or AI Security Libraries
  • AI RE/debugging toolsAI Security Tools & Frameworks → AI Reverse Engineering
  • AI vulnerability scannersAI Security Tools & Frameworks → AI Vulnerability Detection
  • BenchmarksBenchmarks & Standards
  • MCP security toolsAI Pentesting & Red Teaming → AI Security MCP Tools

Quality Bar

  • Prefer canonical repos
  • Avoid forks unless they add meaningful features
  • Add short descriptions
  • Never duplicate an existing URL
  • Tool must be AI/ML-focused

Key Vendor Tools

Vendor Tools
Microsoft Counterfit, PyRIT
Meta PurpleLlama (Llama Guard, Prompt Guard, Code Shield)
NVIDIA Garak, NeMo Guardrails
IBM Adversarial Robustness Toolbox (ART)
Google OSS-Fuzz-Gen
ProtectAI Rebuff, LLM Guard, ModelScan

Read the full file on GitHub · 92 lines

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.

  1. 10d ago First seen · 92 lines · 29 tokens per session scan A c9d1fdd71270

Subscribe to this mod's changes

ai-security-tooling is a skill published in the GitHub repository gmh5225/awesome-ai-security (45 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 699 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-30.

Related

Other skills, from other repositories

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens