Skip to content
New

DeepSeek V4.1 Flash free for 7 days: 10M tokens a day after a top-up of $10 or more. Until Nov 30.

How it works
noorqureshi/ai-supply-chainAI, agents and MCP

ai-supply-chain

⁨Attack the ML/LLM supply chain — poisoned models, datasets, plugins, and unsafe model deserialization. Load when an app loads third-party models/weights (HuggingFace, .pt/.pkl/.h5), installs ML deps, uses plugins/extensions, or fine-tunes on external data. Signals: torch.load, pickle model files, mo⁩

v2026.10.14-ee0e0c53 installs+3 in 7 days27 StarsMITsynced 22 hours ago

Install

No NotHoly CLI yet? Install it first.

$ curl -fsSL https://notholy.com/install.sh | sh
$ notholy skills install noorqureshi/ai-supply-chain

Writes to ⁦~/.notholy/skills⁩ after checking the signature and the SHA-256.

SignatureSigned, ed25519
dfEvf9UC+Z…7ukBFoBg==The CLI checks the SHA-256 and the signature before it writes a file.
Package29890b2e…56e9d1ed
29890b2e2d1c…dfae56e9d1ed1 file · ⁦1.5 KB⁩
ScanLowno findings
The scan found nothing to flag in this version.See the full scan
Sourcegithub.com/NoorQureshi/security-skills/tree/main/skills/ai-ml/ai-supply-chain@ee0e0c5

When it applies

The target consumes third-party ML artifacts: downloaded model weights, datasets, tokenizers, plugins/extensions, or fine-tuning data. Each is code or data that runs with the app's trust.

Why it works

Model files are frequently pickle-based (torch.load, .pkl, joblib) — loading them executes arbitrary code (__reduce__), so a malicious model on a hub is RCE on whoever loads it. Datasets and RAG corpora poison behavior; plugins/extensions run with the assistant's privileges; typosquatted ML packages inject code at install.

Method

  1. Unsafe model deserialization (RCE): if the app torch.load/pickle.loads a model you can supply or influence, craft a pickle with a __reduce__ payload (fickling), or scan a suspect model (fickling, modelscan) for embedded code. Prefer safetensors as the safe alternative.
  2. Model/dataset poisoning: contribute or substitute a model/dataset that carries a backdoor (trigger phrase → attacker-chosen output) or degrades safety — relevant when the app auto-pulls "latest" from a hub or fine-tunes on user/external data.
  3. Plugin / extension abuse: a malicious or over-permissioned plugin the assistant loads → data access, tool abuse (→ ai-agent-tool-abuse).
  4. Dependency attacks: typosquat/dependency-confusion on ML packages (→ web-dependency-confusion); compromised requirements.
  5. Provenance checks: verify signatures/hashes, pinned versions, and safetensors usage.

Gotchas

  • .pt/.bin/.pkl = code execution on load; .safetensors = data only. The file format is the tell.
  • Auto-updating to a hub's "latest" model/plugin is the poisoning entry point — flag it.
  • Prove RCE with a benign payload (OOB callback), never a destructive one; mind scope/RoE.

Verify success

Code execution when a crafted model/artifact is loaded (OOB beacon), a demonstrated backdoor trigger, or a poisoned dependency/plugin executing in the app's context.

References

OWASP LLM Top 10 (2025) LLM03/LLM04; fickling & modelscan; safetensors; "pickle is not secure".

Files in this version

Permissions

PermissionDeclaredFound by the scan
Reads filesNoNo
Writes filesNoNo
Runs shell commandsNoNo
Uses the networkNoNo
Uses connectorsNoNo
Drives a browserNoNo

Scan findings

Reviewed on Nov 13, 2026

The scan found nothing to flag in this version.

A clean scan lowers the risk but does not prove a package is safe. Read what you install.

VersionPublishedCommitSHA-256SignaturePermission change
v2026.10.14-ee0e0c5Nov 13, 2026ee0e0c529890b2eSigned–

Ask anything your scope allows.

Create an account, add credits and ask the first question in the chat or the terminal.

  1. 1/3

    Create the account

    Individual or company. You can switch to a company later without losing balance or keys.

    IndividualCompany
  2. 2/3

    Add credits

    By card. Pay per token, no subscription.

    $5.00minimum deposit
  3. 3/3

    Ask

    In the chat, or install the CLI and run notholy login in your terminal.

    $ notholy login