ai model report

Is openbmb/MiniCPM-o-4_5-awq safe to load?

LOW risk. 6 of 117 tracked dependencies carry advisories. Driven by No version-matched advisories and no malicious packages..

View on HuggingFace

// posture
advisories 100provenance 75resolution 100xyz safety 100load safety 60supply chain 100scanner trust 100code execution 25
fig. 01 — posture on eight axes, 100 is clean. Weakest: code execution at 25.
// the finding
0.0xyz score out of 10LOW

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

3 more findings on this model.

Author
openbmb
Task
any-to-any
Loader
transformers
License
apache-2.0
Downloads
56,669
Remote code
ships Python that runs on load (trust_remote_code)
// dependencies

28 direct, 21 with findings, 104 reachable

PackageEvidenceAdvisoriesWorst
pillowdirect, runtime71none pinned
transformersdirect, runtime23none pinned
Create a free accountto see all 117 dependencies, which versions are pinned, and what to change.
// what changed
  • MEDIUMvector new2026-09-09
  • MEDIUMvector new2026-09-09
  • MEDIUMrisk level raised (unknown to low)2026-09-09

Risk computed 2026-09-22 at 19:00 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.
Is openbmb/MiniCPM-o-4_5-awq safe to load? AI model security report | CyberXYZ