ai-drug-design-scientist
Warn
Audited by Snyk on Apr 21, 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 explicitly ingests public third‑party resources (e.g., AlphaFold/PDB structures and public databases like ZINC15/ChEMBL/BindingDB referenced in references/overview.md and the Example 1 code block showing "zinc15_2m"), which the agent is expected to read and use to drive screening, modeling, and decision-making, exposing it to untrusted external content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata