tooluniverse-hla-immunogenomics
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data (HLA alleles, pathogens) and results from external biomedical databases (IMGT, IEDB, UniProt), which could potentially contain adversarial instructions.
- Ingestion points: User input strings and API responses from the
IMGT,IEDB,BVBRC, andUniProttools. - Boundary markers: No specific boundary markers or instructions to ignore embedded commands in external data are provided in the prompts.
- Capability inventory: The skill uses
bashto execute generated Python code and performs network queries via built-in tools. - Sanitization: The instructions do not specify sanitization or validation logic for the data before it is processed by the generated Python scripts.
- [DYNAMIC_EXECUTION]: The skill instructs the agent to generate and execute Python code at runtime to handle statistical computation and data visualization.
- Evidence: The 'COMPUTE, DON'T DESCRIBE' section explicitly directs the agent to 'write and run Python code via Bash' to analyze data retrieved from ToolUniverse tools.
Audit Metadata