Splinter0/tensorflow-rce

RCE PoC for Tensorflow using a malicious Lambda layer

40
/ 100
Emerging

This project helps security researchers understand how a malicious remote code execution payload can be embedded within a TensorFlow machine learning model. It demonstrates how an attacker could craft a model file (an .h5 file) to include a reverse shell, and how that model could be used to compromise a system when loaded. Security professionals and penetration testers working with machine learning systems would use this to investigate potential vulnerabilities.

No commits in the last 6 months.

Use this if you are a security researcher or penetration tester looking to understand and demonstrate remote code execution vulnerabilities in TensorFlow models.

Not ideal if you are a data scientist or machine learning engineer looking for tools to build or deploy secure models, as this is an exploit demonstration, not a defensive tool.

penetration-testing vulnerability-research ML-security red-teaming application-security
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

61

Forks

8

Language

Python

License

MIT

Category

ai-red-teaming

Last pushed

Jul 30, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Splinter0/tensorflow-rce"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.