pathway-enrichment

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

• Third-party content exposure detected (medium risk: 0.65). At runtime, the skill calls gseapy.enrichr(...) (online ORA) and gp.prerank(...) (GSEA) with gene_sets library names, which causes gseapy to fetch gene-set definitions/results from external services (Enrichr/MSigDB) and ingest that returned text/metadata into the LLM context via the agent’s tool outputs.