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's SKILL.md/REFERENCE.md explicitly uses ToolUniverse calls (e.g., PubMed_search, Enrichr_submit_genelist / Enrichr_get_results, DGIdb_query_gene, GEO_get_dataset, ArrayExpress_get_experiment) to fetch and ingest data from public literature/databases and then uses those results to drive prioritization and downstream decisions, exposing the agent to untrusted third-party content that could contain instructions or influence actions.