tooluniverse-disease-research

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md and TOOLS_REFERENCE.md) instructs the agent to fetch and ingest results from multiple public third‑party sources—e.g., PubMed_search_articles, search_clinical_trials (ClinicalTrials.gov), OpenTargets, ClinVar, GWAS Catalog, OpenAlex, Europe_PMC—and to read/synthesize those outputs into the progressive report (update_report_section), meaning externally provided content is actively interpreted and can materially influence subsequent synthesis and actions.