bio-single-cell-scatac-analysis
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing dependencies from well-known and authoritative sources. It specifically instructs the user to install the ArchR package from the Greenleaf Lab's official GitHub repository using the
devtools::install_github('GreenleafLab/ArchR')command. It also leverages standard package managers such aspipfor Python andinstall.packagesorBiocManagerfor R to acquire necessary libraries.- [COMMAND_EXECUTION]: The usage guide provides standard shell commands for environment setup, including the installation of Python dependencies (pip install snapatac2 scanpy). Additionally, the workflows require external bioinformatics tools, specifically MACS2 or MACS3, to be available on the system PATH for peak calling operations.- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for processing external genomic data. - Ingestion points: The analysis scripts ingest user-provided data files, such as
fragments.tsv.gz,filtered_peak_bc_matrix.h5, andsinglecell.csvas evidenced inexamples/scatac_workflow.pyandexamples/signac_workflow.R. - Boundary markers: The skill does not employ explicit boundary markers or instructions to disregard potentially embedded instructions within the metadata of processed files.
- Capability inventory: The skill performs file system read/write operations and executes complex computational logic within Python and R environments.
- Sanitization: Content validation or sanitization of the genomic data files is not performed prior to processing, which is consistent with the intended scientific use case of the skill.
Audit Metadata