ai model report

Is jamesheald/joint-space-empowerment safe to load?

CLEAN risk. 2 of 31 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 20.

// the finding

0.0xyz score out of 10CLEAN

INFO2 package(s) in the runtime/inferred stack carry advisories. Not counted toward risk — no version is declared, so we can't say which one gets installed.

Author: jamesheald
Task: reinforcement-learning
Loader: stable-baselines3
License: mit
Downloads: 312,668
Remote code: not required

// dependencies

4 direct, 2 with findings, 27 reachable

Package	Evidence	Advisories	Worst
torch	direct, inferred	13	none pinned
numpy	direct, inferred	8	none pinned
gymnasium	direct, install	0	hidden
stable-baselines3	direct, install	0	hidden
cloudpickle	direct, install	0	hidden
cuda-bindings	direct, install	0	hidden
cuda-pathfinder	direct, install	0	hidden
cuda-toolkit	direct, install	0	hidden

Create a free accountto see all 31 dependencies, which versions are pinned, and what to change.

Risk computed 2026-09-22 at 18:52 UTC. Dependencies come from the model's requirements, its declared loader and the code it ships; advisories from NVD, GHSA and OSV.