unboundcompute/security-agent-skills · skills/auditing-ml-model-supply-chain/SKILL.md

auditing-ml-model-supply-chain skillA

auditing-ml-model-supply-chain is agent-read markdown (skill) from unboundcompute/security-agent-skills: Audit the machine-learning models you load as untrusted code, not just data. Covers deserialization RCE from unsafe checkpoint formats (a model file that runs code on load), poisoned or backdoored weights, tampered or trojaned models pulled from a public hub, name and version confusion for model artifacts, and skipped integrity verification. Use when adding a model, checkpoint, or weights file to a pipeline, reviewing where models are loaded, or vetting a third-party model. A model file is execu.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

How to install

Latest version
mdr add unboundcompute/security-agent-skills/auditing-ml-model-supply-chain@git:20260816.a0bc1d1
Exact content
mdr add unboundcompute/security-agent-skills/auditing-ml-model-supply-chain@sha256:bf6398d682d9a5d1

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_i2umysshgqd7hvqm.svg)](https://markdownregistry.com/a/art_i2umysshgqd7hvqm)

0 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260816.a0bc1d1 latest2026-08-16 a0bc1d1 6,592 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6592 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

unboundcompute/security-agent-skills · 5 stars · license MIT · pushed 2026-09-08 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_i2umysshgqd7hvqm
GET https://markdownregistry.com/api/v1/resolve?ref=unboundcompute/security-agent-skills/auditing-ml-model-supply-chain
GET https://markdownregistry.com/api/v1/blob/bf6398d682d9a5d1dd2882883652fefacadd64f4417467eef33e9fb80556ebf2

Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.