tooluniverse-crispr-screen-analysis

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests content from public third-party sources (e.g., PubMed_search, Enrichr_submit_genelist/Enrichr_get_results, DGIdb_query_gene, DepMap_get_gene_dependencies and OpenTargets_get_target calls shown in SKILL.md/FALLBACK_PATCH.md), and those external, untrusted literature/database results are parsed and used to drive essentiality classification, prioritization, and follow-up actions—so external content can materially influence tool actions and decisions.