tooluniverse-cancer-variant-interpretation
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill orchestrates legitimate bioinformatics research workflows using platform-provided tool interfaces to access established databases like MyGene, UniProt, CIViC, cBioPortal, and OpenTargets.
- [SAFE]: No prompt injection patterns or instructions to bypass safety guidelines were found. The instructions focus on structured data retrieval and clinical reporting.
- [SAFE]: No data exfiltration, hardcoded credentials, or unauthorized network operations were detected. All API interactions target well-known scientific and medical services.
- [SAFE]: The skill does not employ any obfuscation, persistence, or privilege escalation techniques.
- [COMMAND_EXECUTION]: The skill includes instructions to generate markdown reports on the local file system. This functionality is consistent with its stated purpose of creating clinical interpretation reports and does not involve arbitrary or dangerous command execution.
Audit Metadata