ensembl-database

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install standard Python packages ensembl_rest and requests. These are established libraries for bioinformatics and HTTP requests respectively.
  • [COMMAND_EXECUTION]: The skill contains a Python script scripts/ensembl_query.py that facilitates querying the Ensembl API. It uses the requests library for network operations and does not perform any dangerous shell command execution or local file system modifications.
  • [DATA_EXFILTRATION]: Network operations are directed exclusively to well-known genomic database domains: rest.ensembl.org and grch37.rest.ensembl.org. No sensitive local files or environment variables are accessed or transmitted.
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves data from an external source (Ensembl REST API).
  • Ingestion points: scripts/ensembl_query.py and code examples in SKILL.md via requests calls.
  • Boundary markers: Absent; the data is returned as raw JSON or text to the agent context.
  • Capability inventory: The skill is limited to network reads and printing output; it lacks file-write or subprocess capabilities.
  • Sanitization: Absent; however, the data retrieved (genomic sequences and annotations) is treated as informational data rather than executable logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 08:21 AM
Security Audit — agent-trust-hub — ensembl-database