tooluniverse-systems-biology
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data (gene lists, protein IDs, and search keywords) which are then interpolated into tool parameters for external database queries.
- Ingestion points: Data enters the skill via the
gene_listparameter inenrichr_gene_enrichment_analysis, theidparameter inReactome_map_uniprot_to_pathways, andquery/keywordparameters in various search tools. - Boundary markers: The skill does not explicitly instruct the agent to use boundary markers or delimiters when processing these inputs.
- Capability inventory: The skill has the capability to perform network operations (via specific biological API tools) and write findings to a markdown report file.
- Sanitization: There are no instructions for sanitizing or validating the input data before processing.
Audit Metadata