alterlab-datamol
Warn
Audited by Snyk on Apr 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests arbitrary remote files via fsspec (see SKILL.md "Remote file support (S3, GCS, HTTP)" and references/io_module.md examples like dm.read_csv("https://example.com/data.csv") and dm.read_sdf("s3://bucket/compounds.sdf")), meaning untrusted third‑party content is read and used in workflows that affect processing and selection decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata