ai model report

Is sentence-transformers/all-mpnet-base-v2 safe to load?

CLEAN risk. 5 of 122 tracked dependencies carry advisories. Driven by No version-matched advisories and no malicious packages..

View on HuggingFace

// posture

fig. 01 — posture on eight axes, 100 is clean. Weakest: load safety at 60.

// the finding

0.0xyz score out of 10CLEAN

LOWShips both safetensors and 3 pickle-format file(s); a consumer passing use_safetensors=False takes the pickle path.

2 more findings on this model.

Author: sentence-transformers
Task: sentence-similarity
Loader: sentence-transformers
License: apache-2.0
Downloads: 23,432,230
Remote code: not required

// dependencies

10 direct, 8 with findings, 115 reachable

Package	Evidence	Advisories	Worst
transformers	direct, runtime	23	none pinned
torch	direct, runtime	13	none pinned
numpy	direct, install	8	hidden
scikit-learn	direct, install	3	hidden
tqdm	direct, install	2	hidden
sentence-transformers	direct, install	0	hidden
torch-xla	direct, install	0	hidden
absl-py	direct, install	0	hidden

Create a free accountto see all 122 dependencies, which versions are pinned, and what to change.

Risk computed 2026-09-22 at 18:47 UTC. Dependencies come from the model's requirements, its declared loader and the code it ships; advisories from NVD, GHSA and OSV.