tooluniverse-admet-prediction

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly instructs the agent to fetch and ingest data from public third-party databases (e.g., PubChem via PubChem_get_CID_by_compound_name and PubChem_get_compound_properties_by_CID, PubChemTox_get_* calls, and ChEMBL_get_molecule) and uses that data to drive scorecard verdicts and next actions, so external public content can materially influence decisions.