tooluniverse-acmg-variant-classification
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources such as PubMed, ClinVar, and UniProt which could theoretically contain malicious instructions designed to influence the agent's reasoning.
- Ingestion points: Data fetched from external tools including
PubMed_search_articles,ClinVar_get_variant_details, andUniProt_get_function_by_accession(SKILL.md). - Boundary markers: The skill uses structured Markdown templates for the final report, providing some structural separation, but does not explicitly instruction the agent to ignore instructions embedded within the fetched data.
- Capability inventory: The skill uses a variety of database lookup tools and a mechanism explanation tool; it does not contain capabilities for arbitrary shell command execution or persistent file system modifications.
- Sanitization: The instructions do not specify sanitization or filtering logic for text fetched from external biological and clinical databases.
Audit Metadata