precision-medicine-therapeutics
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted patient-specific genomic and clinical data, establishing a surface for indirect prompt injection.
- Ingestion points: Patient genotype data and next-generation sequencing (NGS) results described in SKILL.md.
- Boundary markers: Absent; the skill does not define specific delimiters or instructions to ignore commands embedded within patient data.
- Capability inventory: No high-risk capabilities such as file system writing, arbitrary shell execution, or network exfiltration were identified in the skill body.
- Sanitization: None described.
- [COMMAND_EXECUTION]: The skill provides instructions for a CLI-based installation.
- Includes a setup command using npx to fetch the skill from the author's official GitHub repository.
- [EXTERNAL_DOWNLOADS]: The skill integrates data and references from well-known medical and scientific domains.
- References evidence-based guidelines from trusted sources including ncbi.nlm.nih.gov (ClinVar), cpicpgx.org (CPIC), and pharmgkb.org.
Audit Metadata