tooluniverse-variant-functional-annotation
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external scientific databases such as ClinVar and gnomAD. While this constitutes an ingestion of untrusted data, these are structured academic sources, and the skill provides a rigorous reasoning framework to ensure the agent interprets the data within a scientific context.
- [DYNAMIC_EXECUTION]: The skill encourages the agent to write and execute Python scripts using standard libraries like pandas and scipy to perform statistical analysis on retrieved data. This behavior is consistent with the skill's primary purpose of data analysis and does not involve unsafe operations or untrusted external code.
Audit Metadata