boron-nmr-predict
Warn
Audited by Snyk on Mar 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's installer/runtime (scripts/ensure_model.py) explicitly downloads model files from a public Hugging Face repo (default SII-AI4Chem/boron-nmr-predict-model), and the runtime (scripts/predict_boron_nmr.py and src/core/predictor.py) loads those files (including ml_feature_scaler.pkl via pickle and model .pth via torch.load), so untrusted third-party content is fetched and directly influences/integrates into predictions and execution.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata