ai model report

Is HumanCompatibleAI/ppo-seals-CartPole-v0 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
advisories 100provenance 100resolution 100xyz safety 100load safety 20supply chain 100scanner trust 100code execution 100
fig. 01 — posture on eight axes, 100 is clean. Weakest: load safety at 20.
// the finding
not scoredno advisory applies to a version this model pinsCLEAN

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
HumanCompatibleAI
Task
reinforcement-learning
Loader
stable-baselines3
Downloads
104,641
Remote code
not required
// dependencies

4 direct, 2 with findings, 27 reachable

PackageEvidenceAdvisoriesWorst
torchdirect, inferred13none pinned
numpydirect, inferred8none pinned
Create a free accountto see all 31 dependencies, which versions are pinned, and what to change.

Risk computed 2026-09-24 at 07:51 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 HumanCompatibleAI/ppo-seals-CartPole-v0 safe to load? AI model security report | CyberXYZ