therapeutic-reasoning-chain

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and ingest public third-party content (e.g., DrugBank via go.drugbank.com, OpenTargets API, PubMed eutils, ClinicalTrials.gov) in Step 2 and Step 4 and then uses that content to drive treatment decisions and subsequent tool calls, which clearly exposes the agent to untrusted external content that could influence actions.