skills/internscience/chemclaw/mol-image-to-smiles/Snyk

mol-image-to-smiles

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: 0.70). The script's predict_with_molnextr function (scripts/mol_image_to_smiles.py) calls the public HuggingFace Inference API (model "MolecularAI/MolNextR") and directly uses the returned text as SMILES/best_result, so untrusted third‑party API responses can influence downstream decisions and tool outputs.

Issues (1)

W011

MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata

Risk Level

MEDIUM

Analyzed

Mar 30, 2026, 12:51 AM

Issues

1