mol-2d-viewer
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: 0.80). The skill's name_to_smiles function (scripts/mol_2d_viewer.py) calls the public OPSIN API at https://opsin.ch.cam.ac.uk/opsin/... and parses JSON/CML from that third‑party service to obtain SMILES which are then used to drive rendering and downstream actions, so untrusted remote content can materially influence the agent's behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata