tooluniverse-spatial-omics-analysis

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly calls public third‑party data sources (e.g., PubMed_search_articles and openalex_literature_search in Phase 8, STRING_functional_enrichment, OpenTargets, DGIdb, HPA tools in Phases 1–6) as required steps in the SKILL.md workflow and ingests their untrusted/public content to drive analysis and recommendations, so external content can materially influence the agent's decisions and enable indirect prompt injection.