tooluniverse-comparative-genomics
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [DYNAMIC_EXECUTION]: The skill instructs the agent to generate and execute Python code and bash commands to perform statistical analysis on biological data. This is an intended function of the skill and specifies the use of standard scientific libraries such as pandas, scipy, and statsmodels.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external bioinformatics databases (NCBI, Ensembl, UniProt, Monarch). While this creates an attack surface for untrusted data, the instructions focus on structured data retrieval and specific computational workflows, significantly reducing the risk of accidental instruction following from the retrieved content.
- [COMMAND_EXECUTION]: The skill utilizes a bundled Python script,
scripts/dnds.py, which is executed via the command line to compute evolutionary metrics. Analysis of the script confirms it contains only standard biological computation logic using Python's core libraries, with no network access or unsafe system calls.
Audit Metadata