ai model report

Is fishaudio/drama-3 safe to load?

CLEAN risk. 0 of 1 tracked dependencies carry advisories. Driven by No version-matched advisories and no malicious packages..

View on HuggingFace

// posture
advisories 100provenance 100resolution 80xyz safety 100load safety 60supply chain 100scanner trust 100code execution 100
fig. 01 — posture on eight axes, 100 is clean. Weakest: load safety at 60.
// the finding
not scoredno advisory applies to a version this model pinsCLEAN

LOWShips safetensors plus 1 pickle checkpoint(s) for other tooling (codec.pth); from_pretrained never loads these, even with use_safetensors=False, but code that torch.load()s them directly (a reference implementation, a training script) executes pickle.

Author
fishaudio
Task
text-to-speech
License
other
Downloads
23
Remote code
not required
// dependencies

1 direct

PackageEvidenceAdvisoriesWorst
transformersdirect, authored0none pinned

Risk computed 2026-10-14 at 01:54 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.