ai model report

Is Aleph-Alpha/Kolibri-1 safe to load?

CLEAN risk. 4 of 183 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: advisories at 100.

// the finding

not scoredno advisory applies to a version this model pinsCLEAN

INFO4 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: Aleph-Alpha
Task: text-generation
Loader: vllm
License: apache-2.0
Downloads: 0
Remote code: not required

// dependencies

4 direct, 4 with findings, 179 reachable

Package	Evidence	Advisories	Worst
vllm	direct, runtime	80	none pinned
transformers	direct, inferred	24	none pinned
torch	direct, install	12	hidden
numpy	direct, install	8	hidden
aiocontextvars	direct, install	0	hidden
aiohappyeyeballs	direct, install	0	hidden
aiohttp	direct, install	0	hidden
aiosignal	direct, install	0	hidden

Create a free accountto see all 183 dependencies, which versions are pinned, and what to change.

Risk computed 2026-10-03 at 23:50 UTC. Dependencies come from the model's requirements, its declared loader and the code it ships; advisories from NVD, GHSA and OSV.