ena-database

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill retrieves biological data from ebi.ac.uk (European Bioinformatics Institute), which is a trusted and standard resource in the bioinformatics community.
  • [DATA_EXFILTRATION] (SAFE): No evidence of credential theft or unauthorized data transfer. Network operations are strictly limited to the public ENA API endpoints for sequence and metadata retrieval.
  • [PROMPT_INJECTION] (SAFE): The instructions do not contain any attempts to override system prompts, bypass safety filters, or extract internal agent state.
  • [INDIRECT_PROMPT_INJECTION] (LOW): As a data-ingestion skill, there is a theoretical surface for indirect prompt injection via external API responses from the ENA database. However, this is inherent to the skill's purpose of data retrieval and the source is a highly trusted scientific repository.
  • Ingestion points: API responses from ebi.ac.uk and file downloads via FTP.
  • Boundary markers: None explicitly defined in the provided snippets.
  • Capability inventory: HTTP GET requests via requests and bulk downloads via enaBrowserTools.
  • Sanitization: Standard JSON and XML parsing is recommended in the best practices section.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:07 PM