ai-model-privacy-audit

ai-model-privacy-audit is a skill for Claude Code, Codex from onfire7777/universal-ai-skills-library. It costs 63 tokens per session (2,303 once invoked), scanned A, a copy of ai-model-privacy-audit, MIT.

A privacy audit method for AI models that tests whether a trained model reveals information from its training data. It includes tests for memorised records, dataset membership, reconstructed inputs, and inferred sensitive attributes.

In plain words
What is it for?
Use it to test models for training-data extraction, membership inference, model inversion, and attribute inference.
Why use it?
It exposes information leakage that may not be visible during ordinary model testing and supports privacy-risk assessment before or after deployment.

Skill for Claude CodeCodex

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

Good fit Use it to test models for training-data extraction, membership inference, model inversion, and attribute inference.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/onfire7777/universal-ai-skills-library/ai-model-privacy-audit
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 onfire7777/universal-ai-skills-library --skill ai-model-privacy-audit
Clone the repo
git clone --depth 1 https://github.com/onfire7777/universal-ai-skills-library

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-model-privacy-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/onfire7777/universal-ai-skills-library/ai-model-privacy-audit/github.svg)](https://agentmods.dev/skills/onfire7777/universal-ai-skills-library/ai-model-privacy-audit)
Your own site
<a href="https://agentmods.dev/skills/onfire7777/universal-ai-skills-library/ai-model-privacy-audit"><img src="https://agentmods.dev/badge/skills/onfire7777/universal-ai-skills-library/ai-model-privacy-audit/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-model-privacy-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/onfire7777/universal-ai-skills-library/ai-model-privacy-audit"><img src="https://agentmods.dev/badge/skills/onfire7777/universal-ai-skills-library/ai-model-privacy-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,303 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.
Origin 97% 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 $0.00063 $0.02303
Opus 5 $0.00032 $0.01151
Sonnet 5 $0.00013 $0.00461
Haiku 4.5 $0.00006 $0.00230

Measured 9d ago against content hash 79e5d3a4a5f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ai-model-privacy-audit 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/process.py), 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.

Origin

This is a copy

97% identical to ai-model-privacy-audit — 19 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.

skills/ai-model-privacy-audit/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Model Privacy Audit

Overview

AI model privacy auditing is the systematic assessment of whether trained ML models leak information about their training data. Models can memorize individual training records, enabling adversaries to extract personal data, determine dataset membership, reconstruct input features, or infer sensitive attributes. This skill implements a comprehensive model privacy audit methodology using established attack techniques and tools (ML Privacy Meter, ART, Foolbox) to quantify privacy leakage before deployment and periodically during operation. The audit results feed directly into the AI DPIA risk assessment and inform mitigation measure selection.

Privacy Attack Taxonomy

1. Training Data Extraction

Objective: Extract verbatim or near-verbatim records from the model's training data.

Attack Vector Description Target Models
Prompt-based extraction Craft prompts that cause LLMs to regurgitate training data Language models, generative models
Canary extraction Insert known canary strings into training data and test if model reproduces them Any model (testing methodology)
Gradient-based extraction Use model gradients to reconstruct training inputs Models with accessible gradients
Generative reconstruction Use the model as an oracle to iteratively reconstruct training samples GANs, VAEs, diffusion models

Risk Factors Increasing Extraction Likelihood:

  • Large model capacity relative to training data size (overfitting)
  • Training data containing duplicated or near-duplicated records
  • Longer training duration (more epochs)
  • Lower regularisation
  • Models with high output granularity (logits, probabilities)

Testing Methodology:

  1. Insert canary records with unique identifiers into training data
  2. Train the model
  3. Attempt extraction through various prompting strategies
  4. Measure extraction success rate (percentage of canaries recovered)
  5. Threshold: extraction rate should be below 0.1% for acceptable risk

Read the full file on GitHub · 205 lines

Files

What ships with it

4 files beside SKILL.md 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.

  1. 9d ago First seen · 205 lines · 63 tokens per session scan A 79e5d3a4a5f9

Subscribe to this mod's changes

ai-model-privacy-audit is a skill published in the GitHub repository onfire7777/universal-ai-skills-library (16 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 2,303 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to ai-model-privacy-audit, differing in 19 lines, and is treated as a copy.

Related

Other skills, from other repositories

vs-crawler

Crawl websites (news, blogs, papers, GitHub, product docs, RSS feeds) into a fixed-schema JSONL file, then create a dataset and a searchable application in Viking AI Search. Supports one-time crawl and scheduled recurring crawl with automatic incremental sync.

volcengine/SearchCLI · 57 tokens

vs-search-tuning

Use when a user asks an agent to evaluate or tune text search similarity for an existing Viking AI Search application and dataset.

volcengine/SearchCLI · 29 tokens

building-agents

Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…

ericrisco/rsc-harness · 85 tokens

agent-eval

Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…

ericrisco/rsc-harness · 79 tokens

ai-ml-development

AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.

travisjneuman/.claude · 43 tokens

data-engineering

ETL/ELT pipelines, data warehousing (BigQuery, Snowflake, Redshift), stream processing (Kafka, Spark Streaming), orchestration (Airflow, Dagster, Prefect), dbt transformations, and data lake architecture. Use when building data pipelines, designing warehouse schemas, or implementing real-time data processing.

travisjneuman/.claude · 70 tokens