ai model report

Is IDEA-Research/ChatRex-7B safe to load?

CyberXYZ rates IDEA-Research/ChatRex-7B LOW. No version-matched advisories and no malicious packages. It depends on 180 tracked packages, and 4 carry advisories. It ships Python that runs when the model is loaded (trust_remote_code).

View on HuggingFace

// posture
advisories 100provenance 75resolution 80xyz safety 100load safety 100supply chain 100scanner trust 100code execution 25
fig. 01 — posture on eight axes, 100 is clean. Weakest: code execution at 25.
// the finding
not scoredno advisory applies to a version this model pinsLOW

MEDIUMconfig.json declares `auto_map` — from_pretrained(trust_remote_code=True) executes Python shipped in this repo.

2 more findings on this model.

Author
IDEA-Research
Task
image-text-to-text
Downloads
164,012
Remote code
ships Python that runs on load (trust_remote_code)
// dependencies

14 direct, 8 with findings, 172 reachable

PackageEvidenceAdvisoriesWorst
pillowdirect, runtime147none pinned
transformersdirect, runtime24none pinned
Create a free accountto see all 180 dependencies, which versions are pinned, and what to change.
// questions
Is IDEA-Research/ChatRex-7B safe to load?

CyberXYZ does not call a model safe in absolute terms. It rates IDEA-Research/ChatRex-7B LOW. No version-matched advisories and no malicious packages. That covers its dependencies and how it loads, not every file it ships, so treat any check that did not run as unverified and check the exact files before you load them.

What does IDEA-Research/ChatRex-7B depend on?

CyberXYZ tracks 180 dependencies for IDEA-Research/ChatRex-7B, 14 of them direct. 4 carry advisories. They include pillow and transformers. A free account lists all of them.

Does IDEA-Research/ChatRex-7B run code when it loads?

Yes, it can. IDEA-Research/ChatRex-7B ships Python code and HuggingFace marks it trust_remote_code, so loading it with trust_remote_code enabled runs that code on your machine. Read the code first.

How do I check IDEA-Research/ChatRex-7B before loading it?

Run the xyz MCP tool model_load_safety on IDEA-Research/ChatRex-7B to get a verdict on its weight files before you load them, or search it in CyberXYZ Check at https://cyberxyz.io/check?q=IDEA-Research%2FChatRex-7B.


Risk computed 2026-11-14 at 09:47 UTC. Dependencies come from the model's requirements, its declared loader and the code it ships; advisories from NVD, GHSA and OSV.

Model risk is computed from the model's declared and observed Python dependencies and the code it ships. If a finding is wrong, tell us.