tooluniverse-gwas-study-explorer
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external scientific sources, including the NHGRI-EBI GWAS Catalog and Open Targets Genetics. This creates a surface for indirect prompt injection if those external services were to return data containing malicious instructions.
- Ingestion points: Data is retrieved from the GWAS Catalog and Open Targets APIs as described in the tools section of
SKILL.md. - Capability inventory: The skill is limited to data retrieval and statistical comparison; it does not utilize tools for file system modification, command execution, or network exfiltration.
- Boundary markers: There are no explicit instructions or delimiters provided to prevent the agent from interpreting instructions potentially found within the fetched genomic data.
- Sanitization: The skill does not implement specific sanitization routines for the external data it processes.
Audit Metadata