dune-mcp-skill

Warn

Audited by Snyk on Mar 8, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). This skill explicitly calls Dune's public MCP API (https://api.dune.com/mcp/v1) via operations like searchTables and getExecutionResults described in SKILL.md and references/usage-patterns.md, which return public/user-generated table schemas and results that the agent is expected to read and use to choose and build queries, so untrusted third-party content could influence agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 8, 2026, 09:42 AM