ai model report

Is poolside/Laguna-M.1 safe to load?

LOW risk. 4 of 226 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: code execution at 25.

// the finding

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.

1 more finding on this model.

Author: poolside
Task: text-generation
Loader: vllm
License: apache-2.0
Downloads: 115,665
Remote code: ships Python that runs on load (trust_remote_code)

// dependencies

7 direct, 7 with findings, 222 reachable

Package	Evidence	Advisories	Worst
vllm	direct, runtime	69	none pinned
transformers	direct, runtime	23	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 226 dependencies, which versions are pinned, and what to change.

Risk computed 2026-09-27 at 18:46 UTC. Dependencies come from the model's requirements, its declared loader and the code it ships; advisories from NVD, GHSA and OSV.