ai model report

Is perplexity-ai/pplx-decider-v1-27b safe to load?

CyberXYZ rates perplexity-ai/pplx-decider-v1-27b LOW. No version-matched advisories and no malicious packages. It depends on 154 tracked packages, and 10 carry advisories. It does not require trust_remote_code.

View on HuggingFace

// posture
advisories 100provenance 70resolution 100xyz safety 100load safety 100supply chain 100scanner trust 100code execution 70
fig. 01 — posture on eight axes, 100 is clean. Weakest: provenance at 70.
// the finding
not scoredno advisory applies to a version this model pinsLOW

LOWThe repo's commit SHA changed since we first saw it — weights were replaced.

1 more finding on this model.

Author
perplexity-ai
Task
text-classification
Loader
pytorch
License
apache-2.0
Downloads
2,338
Remote code
not required
// dependencies

27 direct, 23 with findings, 141 reachable

PackageEvidenceAdvisoriesWorst
pillowdirect, runtime147none pinned
transformersdirect, runtime24none pinned
Create a free accountto see all 154 dependencies, which versions are pinned, and what to change.
// questions
Is perplexity-ai/pplx-decider-v1-27b safe to load?

CyberXYZ does not call a model safe in absolute terms. It rates perplexity-ai/pplx-decider-v1-27b LOW. No version-matched advisories and no malicious packages. That covers its dependencies and how it loads, not every file it ships, so treat any check that did not run as unverified and check the exact files before you load them.

What does perplexity-ai/pplx-decider-v1-27b depend on?

CyberXYZ tracks 154 dependencies for perplexity-ai/pplx-decider-v1-27b, 27 of them direct. 10 carry advisories. They include pillow and transformers. A free account lists all of them.

Does perplexity-ai/pplx-decider-v1-27b run code when it loads?

HuggingFace does not mark perplexity-ai/pplx-decider-v1-27b as requiring trust_remote_code. That says nothing about the format of its weight files, which model_load_safety checks per file.

How do I check perplexity-ai/pplx-decider-v1-27b before loading it?

Run the xyz MCP tool model_load_safety on perplexity-ai/pplx-decider-v1-27b to get a verdict on its weight files before you load them, or search it in CyberXYZ Check at https://cyberxyz.io/check?q=perplexity-ai%2Fpplx-decider-v1-27b.


Risk computed 2026-11-22 at 16:00 UTC. Dependencies come from the model's requirements, its declared loader and the code it ships; advisories from NVD, GHSA and OSV.

Model risk is computed from the model's declared and observed Python dependencies and the code it ships. If a finding is wrong, tell us.