precision-medicine-therapeutics

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill's primary function is to process patient-specific clinical data and genomic results, which introduces a surface for indirect prompt injection attacks where malicious instructions could be embedded in the input data.
  • Ingestion points: Processes untrusted patient inputs such as "Patient genotype", "NGS results", and "Current medication" as described in SKILL.md.
  • Boundary markers: Absent. The skill does not define explicit delimiters or instructions to the model to ignore potential commands within the patient data.
  • Capability inventory: Low. The skill is documented to perform interpretation and recommendation tasks in SKILL.md and does not describe capabilities for arbitrary shell execution, file system modification, or unauthorized network exfiltration.
  • Sanitization: Absent. No documentation exists regarding the validation or sanitization of input data before processing.
  • [EXTERNAL_DOWNLOADS]: The skill provides installation instructions that use a package manager to fetch resources from the author's repository.
  • Evidence: The instruction npx skills add Open-Medica/open-medical-skills in SKILL.md downloads and executes content from the vendor's repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 01:04 PM
Security Audit — agent-trust-hub — precision-medicine-therapeutics