ena-database
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches biological and genomic records from the European Bioinformatics Institute (EBI) official infrastructure at ebi.ac.uk. This aligns with the skill's stated purpose.
- [PROMPT_INJECTION]: The skill ingests external data (metadata, annotations) from the ENA database, creating a surface for indirect prompt injection where untrusted data could influence agent behavior.
- Ingestion points: API responses in JSON, XML, and TSV formats are retrieved across various endpoints defined in references/api_reference.md.
- Boundary markers: The provided documentation does not specify the use of delimiters or ignore-instructions for the retrieved data.
- Capability inventory: The skill focus is on data retrieval using the requests library; no dangerous execution capabilities such as subprocess or eval are demonstrated or requested in the provided scripts.
- Sanitization: The documentation correctly advises using formal XML and JSON parsing libraries to handle external data safely.
Audit Metadata