tooluniverse-small-molecule-discovery

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and even scrapes data from public third-party sources (PubChem, ChEMBL, BindingDB, SwissADME/SwissTargetPrediction, eMolecules, Enamine) and requires the agent to read and act on returned SMILES, activity and ADMET data as part of its workflow, so external content could materially influence subsequent tool calls and decisions.