tooluniverse-single-cell
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by design, as it is intended to ingest and process untrusted external genomic and expression data files.
- Ingestion points: The skill reads data using
sc.read_h5ad(),sc.read_10x_mtx(), andpd.read_csv()as seen inSKILL.mdandreferences/scanpy_workflow.md. - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potential commands embedded within the data (e.g., in gene metadata or cell annotations).
- Capability inventory: The skill utilizes subprocess execution for analysis and performs network operations through
ToolUniverseAPI calls (e.g.,OmniPath_get_ligand_receptor_interactions,MyGene_query_genes). - Sanitization: No explicit sanitization or filtering of external content is defined in the instructions beyond standard library-level data parsing.
Audit Metadata