dune

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates data retrieval from the official Dune Analytics API at https://api.dune.com/api/v1, which is a well-known service for on-chain data analytics.
  • [SAFE]: Authentication is managed via the DUNE_API_KEY environment variable, adhering to security best practices for credential handling.
  • [PROMPT_INJECTION]: The skill contains a surface for processing data from external SQL queries (Category 8).
  • Ingestion points: Response data from GET /execution/{id}/results and GET /query/{id}/results as described in SKILL.md.
  • Boundary markers: No specific delimiters or safety instructions are defined for the agent when processing the external JSON results.
  • Capability inventory: The skill is restricted to performing HTTP GET/POST requests to the Dune API; it does not request local command execution, file system access, or additional network operations.
  • Sanitization: The skill utilizes query_parameters (e.g., {{wallet_address}}) to safely pass values into SQL queries, preventing remote SQL injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 07:23 AM