tooluniverse-systems-biology
Warn
Audited by Snyk on Mar 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill explicitly queries and ingests public, third‑party databases (e.g., KEGG, WikiPathways, Pathway Commons, BioModels, Enrichr, Reactome) as shown in SKILL.md Phase 3 and in python_implementation.py (tu.tools.kegg_search_pathway, WikiPathways_search, pc_search_pathways, biomodels_search, enrichr_gene_enrichment_analysis, Reactome_map_uniprot_to_pathways), and those external results are parsed and used to drive decisions (e.g., choose top pathways, fetch reactions, and generate follow-up queries), so untrusted/user-contributed content could indirectly influence agent behavior.
Audit Metadata