alterlab-ensembl
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses established scientific data sources (EMBL-EBI Ensembl) and standard HTTP communication. The Python script in
scripts/ensembl_query.pyimplements proper rate limiting and error handling without any suspicious operations. - [INDIRECT_PROMPT_INJECTION]: The skill fetches data from an external network source, which is an inherent surface for indirect prompt injection.
- Ingestion points: Genomic data is retrieved from
https://rest.ensembl.organdhttps://grch37.rest.ensembl.orgvia theEnsemblAPIClientinscripts/ensembl_query.py. - Boundary markers: Data is returned as structured JSON or sequence strings; no specific boundary delimiters are used to separate external content from agent instructions.
- Capability inventory: The skill uses
Bash(python:*)to execute the query script andWebFetchfor API interaction. - Sanitization: The skill relies on the Ensembl API for data integrity and does not perform additional sanitization of the genomic annotations before they are processed by the agent.
Audit Metadata