auditing-ml-model-supply-chain

auditing-ml-model-supply-chain is a skill for Claude Code from UnboundCompute/security-agent-skills. It costs 117 tokens per session (1,505 once invoked), scanned A, original, MIT.

A security review of machine-learning models and checkpoint files before they enter a training or inference system. It treats model files as potentially executable or behavior-changing content, not merely stored numbers.

In plain words
What is it for?
Inventorying model-loading paths, file formats, producers, and sources. Reviewing how models are loaded and assessing third-party models in a contained environment.
Why use it?
Some model formats can run code while loading, and even files containing only weights may contain hidden backdoors. Publicly hosted or third-party models can therefore compromise a computer or silently change results.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the security-agent-skills plugin — 194 skills shipped together

Good fit Inventorying model-loading paths, file formats, producers, and sources. Reviewing how models are loaded and assessing third-party models in a contained environment.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/unboundcompute/security-agent-skills/auditing-ml-model-supply-chain
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 UnboundCompute/security-agent-skills --skill auditing-ml-model-supply-chain
Clone the repo
git clone --depth 1 https://github.com/UnboundCompute/security-agent-skills

Made for: Claude Code.

Or install security-agent-skills, the plugin that ships this one along with the rest of its 194 skills.

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 auditing-ml-model-supply-chain

README.md
[![agentmods](https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-ml-model-supply-chain/github.svg)](https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-ml-model-supply-chain)
Your own site
<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-ml-model-supply-chain"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-ml-model-supply-chain/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 auditing-ml-model-supply-chain

Your own site · 80×15
<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-ml-model-supply-chain"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-ml-model-supply-chain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,505 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00117 $0.01505
Opus 5 $0.00059 $0.00753
Sonnet 5 $0.00023 $0.00301
Haiku 4.5 $0.00012 $0.00151

Measured 11d ago against content hash bf6398d682d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

auditing-ml-model-supply-chain scanned grade A with 1 finding 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 11d 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.

Unrestricted tool accesslowExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

not: loading one can execute arbitrary code embedded in the file, and even a

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

skills/auditing-ml-model-supply-chain/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Auditing the ML model supply chain: a model file is code you run

A model file is usually treated as inert data, a bag of weights. Many formats are not: loading one can execute arbitrary code embedded in the file, and even a pure-weights model can carry a backdoor that changes behavior on a trigger. The moment your pipeline loads a model someone else produced, that model is untrusted code and untrusted logic entering your system, on the training host, the inference server, or a developer's laptop.

When to use

  • You are adding a model, checkpoint, or weights file to a training or inference pipeline.
  • You are reviewing where and how models are loaded, and from where.
  • You are vetting a third-party or publicly-hosted model before you trust it.

Scope check

Audit models and pipelines you own or are authorized to test. Do not load or execute untrusted model files outside a contained environment. If you can't name the authorization, stop.

The loop

  1. Inventory every model load path and its format. List where the system loads a model, checkpoint, or weights file, who produced each one, and the serialization format. Formats that can reconstruct arbitrary objects execute code on load; formats that carry only tensors are safer. Mark each load site by format risk.

  2. Check for code execution on load (the RCE leg). For any load path using a format that can rebuild arbitrary objects, a malicious file runs code the instant it is loaded, before any inference. Confirm whether untrusted files reach that path, and whether a tensor-only loader or a restricted deserializer is enforced. An unrestricted load of an externally-sourced file is remote code execution.

  3. Trace provenance and integrity. Where did each model come from, and is it verified? Check for a pinned hash or signature, a known publisher, and a fixed version. A model pulled by mutable name from a public hub without hash pinning is a rug-pull and name-confusion channel: the artifact can be swapped, or a lookalike name served.

Read the full file on GitHub · 126 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. 11d ago First seen · 126 lines · 117 tokens per session scan A bf6398d682d9

Subscribe to this mod's changes

auditing-ml-model-supply-chain is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 2d ago), licensed MIT. It adds 117 tokens to every session and 1,505 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

model-supply-chain

Reviews AI/ML model supply chains for security risks including model provenance verification, training data lineage, fine-tuning pipeline integrity, inference dependency review, and backdoor detection. Auto-invoked when reviewing systems that download pre-trained models, fine-tune foundation models, or deploy models…

UnitOneAI/SecuritySkills · 104 tokens

prodcheck-review

Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations and post-launch readiness. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line citations…

FarzamHabibi/pre-production-checklist · 70 tokens

rag-poisoning-and-data-exfiltration

Test Retrieval-Augmented Generation (RAG) systems for data poisoning, prompt injection via retrieved documents, and data exfiltration through manipulated context windows. Use this skill when assessing RAG-based chatbots, knowledge bases, enterprise AI assistants, or any system that augments LLM responses with external…

akashrpatil/awesome-offensive-security-skills · 89 tokens

integrate-arcjet-guard-genkit

Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…

arcjet/arcjet-js · 89 tokens

integrate-arcjet-guard-claude-managed-agents

Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…

arcjet/arcjet-js · 102 tokens

linear-claude-skill

Manage Linear issues, projects, and teams.

Agent-Threat-Rule/agent-threat-rules · 15 tokens