skills.rest
lNwNl
lNwNlCOMMUNITY
Explore all skills by this author →
GitHub

ai-ml-security

Identify security weaknesses across AI/ML model supply chains and adversarial threats.

2|Updated May 15, 2026
Search Tags:#ai security#model extraction#agent security#ml threat modeling#pickle rce#adversarial examples#membership inference
One-click install
npx skills add https://github.com/lNwNl/Methodos --skill ai-ml-security
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-ml-security
Source: https://github.com/lNwNl/Methodos/tree/main/docker/opencode/skills/ai-ml-security
Command: npx skills add https://github.com/lNwNl/Methodos --skill ai-ml-security

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you assess and mitigate security risks across the full AI/ML lifecycle, including model supply chain compromise, adversarial manipulation, training and federated learning poisoning, model extraction, privacy leakage, and LLM/agent-specific threats.

Core Features & Use Cases

  • Model supply chain attack coverage: Detect and reason about risks like pickle-based deserialization RCE in PyTorch artifacts, Hugging Face poisoning (including backdoored weights and malicious tokenizer/config), and dependency confusion in ML pipelines.
  • Adversarial example playbooks: Guide evaluation of robustness using common perturbation methods such as FGSM, PGD, and C&W, including physical-world adversarial considerations.
  • Privacy and extraction threat modeling: Plan tests for membership inference, model inversion, gradient leakage in federated learning, and query-based model stealing/extraction.

Example use case: Before deploying an MLaaS endpoint, run a threat assessment that checks whether untrusted model files could execute code on load, whether the model is robust to adversarial inputs, and whether API responses leak enough information for extraction or membership inference.

Quick Start

Ask an AI agent to run an AI/ML security assessment for your model loading pipeline and inference API, focusing on supply chain integrity, adversarial robustness, and privacy leakage.

Frequently Asked Questions about ai-ml-security

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I assess ML model security risks before deploying an inference API?▼

Assess ML model security risks by running a threat assessment that checks untrusted model files for code execution on load, evaluates adversarial input robustness, and tests API responses for data extraction and membership inference leakage.

What is pickle deserialization RCE in PyTorch model supply chains?▼

Pickle deserialization RCE in PyTorch model supply chains is a security vulnerability where untrusted model files execute arbitrary code upon loading, often involving backdoored weights or malicious tokenizer configurations from repositories like Hugging Face.

How do I test adversarial robustness against FGSM and PGD attacks?▼

Test adversarial robustness against FGSM and PGD attacks by applying perturbation methods to evaluate model resilience against adversarial inputs, including physical-world considerations and C&W attack vectors.

Can I evaluate gradient leakage risks in federated learning training?▼

You can evaluate gradient leakage risks in federated learning training by planning tests for privacy threats like model inversion, membership inference, and gradient leakage during the federated learning training process under adversarial conditions.

Does this AI security assessment cover LLM-driven autonomous agent threats?▼

This AI security assessment covers LLM-driven autonomous agent threats by evaluating agent and tool misuse considerations, providing decision-tree style guidance for securing autonomous agent workflows under adversarial conditions.

Related Skills

Explore More Legal & Compliance Skills→
DorianGalloDorianGallo
5

ai-ml-security

Assess security threats across AI/ML supply chains, adversarial examples, and data privacy.

Community
Advanced
sayseven7sayseven7
11

ai-ml-security

Assess AI and ML systems for supply-chain, adversarial, and privacy risks.

Community
Advanced
huggingfacehuggingface
10.9k

hugging-face-model-trainer

Train and fine-tune language models on Hugging Face Jobs using TRL methods.

Official
Advanced
pluginagentmarketplacepluginagentmarketplace
3

model-inversion

Quantify AI model privacy vulnerabilities via model inversion attacks.

Community
Advanced