ai model report

Is microsoft/Phi-3.5-MoE-instruct safe to load?

MEDIUM risk. 7 of 262 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 100supply 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 10MEDIUM

MEDIUM2 confirmed finding(s) in the transitive closure; declared dependencies alone rate LOW

3 more findings on this model.

Author
microsoft
Task
text-generation
Loader
transformers
License
mit
Downloads
126,470
Remote code
ships Python that runs on load (trust_remote_code)
// dependencies

18 direct, 11 with findings, 250 reachable

PackageEvidenceAdvisoriesWorst
acceleratetransitive, transitive1MEDIUM
acceleratetransitive, transitive1MEDIUM
Create a free accountto see all 262 dependencies, which versions are pinned, and what to change.

Risk computed 2026-09-22 at 18:56 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 microsoft/Phi-3.5-MoE-instruct safe to load? AI model security report | CyberXYZ