alterlab-gwas
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill interacts with the official NHGRI-EBI GWAS Catalog APIs at ebi.ac.uk and ftp.ebi.ac.uk to retrieve genomic association data, which are well-known academic services.
- [INDIRECT_PROMPT_INJECTION]: The skill processes biological association data and trait information from external sources, presenting a theoretical surface for indirect prompt injection.
- Ingestion points: Data is ingested from the GWAS Catalog REST API via the scripts/query_gwas.py script and documented workflows.
- Boundary markers: There are no explicit instructions for the agent to use delimiters when processing the API response content.
- Capability inventory: The skill is configured with Bash(python) and WebFetch capabilities to perform network requests.
- Sanitization: Responses are parsed as JSON by the script before being output to the agent's context.
- [SAFE]: No evidence of prompt injection, data exfiltration, or malicious persistence was found. All network operations and dependencies trace back to reputable academic infrastructure or standard developer libraries.
Audit Metadata