ai model report

Is Agnuxo/CAJAL-4B safe to load?

MEDIUM risk. 3 of 30 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 70.

// the finding

not scoredno advisory applies to a version this model pinsMEDIUM

MEDIUM1 confirmed finding(s) in the transitive closure; declared dependencies alone rate CLEAN

1 more finding on this model.

Author: Agnuxo
Task: text-generation
License: apache-2.0
Downloads: 257,757
Remote code: not required

// dependencies

4 direct, 2 with findings, 27 reachable

Package	Evidence	Advisories	Worst
diskcache	transitive, transitive	1	MEDIUM
requests	direct, runtime	8	none pinned
llama-cpp-python	direct, install	1	hidden
huggingface-hub	direct, install	0	hidden
anyio	direct, install	0	hidden
certifi	direct, install	0	hidden
charset-normalizer	direct, install	0	hidden
click	direct, install	0	hidden

Create a free accountto see all 30 dependencies, which versions are pinned, and what to change.

// what changed

MEDIUMrisk level raised (clean to medium)2026-09-15

Risk computed 2026-11-06 at 21:03 UTC. Dependencies come from the model's requirements, its declared loader and the code it ships; advisories from NVD, GHSA and OSV.