kermt-infer
Warn
Audited by Snyk on Aug 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The workflow reads outsider-authored free text directly from a user-supplied SMILES-only CSV at the “Validate the data” step (
check_data.py --csv /data/<basename>) and then again at “Prepare the data” (prepare_data.py --csv /data/<basename>), before running inference.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata