NYC

ena-database

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTIONNO_CODE
Full Analysis
  • Data Exposure & Exfiltration (LOW): The skill documentation includes examples of network operations targeting ebi.ac.uk, which is not a whitelisted domain for data exfiltration analysis.
  • Indirect Prompt Injection (LOW): The skill creates a surface for indirect prompt injection by facilitating the ingestion of external database records. 1. Ingestion points: Data retrieved via the ENA Portal and Browser APIs. 2. Boundary markers: None specified in the documentation. 3. Capability inventory: The skill is designed for use in bioinformatics pipelines which may have extensive file and system access. 4. Sanitization: No validation or sanitization of retrieved genomic data is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:21 PM