database-lookup

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates data retrieval from 78 reputable scientific, medical, and economic APIs. All target domains (e.g., nasa.gov, ncbi.nlm.nih.gov, worldbank.org, stlouisfed.org) belong to well-known government, academic, or international organizations. These references are documented as part of the skill's intended functionality to provide public data access.
  • [COMMAND_EXECUTION]: Instructions include using curl for specific POST-only APIs (such as Open Targets and gnomAD) and executing Python scripts using the zeep library via a shell to interact with the BRENDA enzyme database, which requires a SOAP interface. These operations are scoped to the primary purpose of the skill and target verified services.
  • [CREDENTIALS_UNSAFE]: The skill provides guidance on managing API keys for several services (e.g., FRED, BEA, Census). It recommends secure practices such as loading keys from environment variables or local .env files and does not contain any hardcoded secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 10:54 PM