tooluniverse-acmg-variant-classification
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a specialized scientific tool designed for healthcare and research contexts, providing structured methodology for genomic variant interpretation.
- [DATA_EXFILTRATION]: No unauthorized data transmission or credential harvesting patterns were found. The skill references an external API key (
ESM_API_KEY) as a functional requirement for a specific computational predictor tool, which is a standard practice for managing access to third-party services. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied variant identifiers (e.g., HGVS strings, rsIDs). While it does not explicitly define sanitization routines for these inputs, the attack surface is minimal as the data is passed to highly specialized bioinformatics APIs rather than being executed as general code or interpreted as complex instructions.
- [REMOTE_CODE_EXECUTION]: The skill does not perform any unauthorized remote code execution, package installations, or dynamic script evaluation. All tool calls described are for legitimate scientific databases and computational services.
Audit Metadata