ai model report

Is LiquidAI/LFM2.5-VL-3B-GGUF safe to load?

MEDIUM risk. 3 of 7 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

0.0xyz score out of 10MEDIUM

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

1 more finding on this model.

Author: LiquidAI
Task: image-text-to-text
Loader: gguf
License: other
Downloads: 30,341
Remote code: not required

// dependencies

2 direct, 2 with findings, 5 reachable

Package	Evidence	Advisories	Worst
diskcache	transitive, transitive	1	MEDIUM
numpy	direct, inferred	8	none pinned
llama-cpp-python	direct, install	1	hidden
jinja2	direct, install	0	hidden
markupsafe	direct, install	0	hidden
numpy	direct, install	0	hidden
typing-extensions	direct, install	0	hidden

Create a free accountto see all 7 dependencies, which versions are pinned, and what to change.

// what changed

MEDIUMvector new2026-09-09
MEDIUMrisk level raised (unknown to medium)2026-09-09

Risk computed 2026-09-22 at 18:47 UTC. Dependencies come from the model's requirements, its declared loader and the code it ships; advisories from NVD, GHSA and OSV.