tooluniverse-spatial-transcriptomics
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and associated code examples focus exclusively on scientific data analysis within the spatial transcriptomics domain. All operations are standard for bioinformatics workflows.
- [EXTERNAL_DOWNLOADS]: The skill describes patterns for retrieving genomic datasets from trusted scientific repositories such as NCBI GEO (ncbi.nlm.nih.gov) and HuBMAP. These downloads use standard Python libraries like
requeststo fetch legitimate research data. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from scientific APIs (UniProt, PubMed, STRING). While this constitutes a potential attack surface for indirect prompt injection, the risk is negligible given the reputable nature of the sources and the domain-specific application (genomics/proteomics).
- [COMMAND_EXECUTION]: Code examples utilize standard Python packages for data science (pandas, scanpy, scikit-learn). There are no attempts to execute arbitrary shell commands, escalate privileges, or interact with sensitive system files.
Audit Metadata