ai model report
Is tencent/Youtu-Parsing-Omni safe to load?
LOW risk. 5 of 190 tracked dependencies carry advisories. Driven by No version-matched advisories and no malicious packages..
not scoredno advisory applies to a version this model pinsLOW
MEDIUMconfig.json declares `auto_map` — from_pretrained(trust_remote_code=True) executes Python shipped in this repo.
2 more findings on this model.
- Author
- tencent
- Task
- image-text-to-text
- Loader
- transformers
- License
- other
- Downloads
- 340
- Remote code
- ships Python that runs on load (trust_remote_code)
37 direct, 24 with findings, 178 reachable
| Package | Evidence | Advisories | Worst |
|---|---|---|---|
| pillow | direct, runtime | 76 | none pinned |
| transformers | direct, runtime | 24 | none pinned |
Create a free accountto see all 190 dependencies, which versions are pinned, and what to change.
Risk computed 2026-10-11 at 00:44 UTC. Dependencies come from the model's requirements, its declared loader and the code it ships; advisories from NVD, GHSA and OSV.