tooluniverse-precision-oncology

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and ingest content from public third‑party sources (e.g., ClinicalTrials.gov, PubMed, BioRxiv/MedRxiv, CIViC, COSMIC, GDC/TCGA, OpenTargets) as part of its required workflow (see SKILL.md and API_USAGE_PATTERNS.md), and that external text is used to drive treatment decisions and follow‑on tool use, so it exposes the agent to untrusted third‑party content that could enable indirect prompt injection.