brandfetch-automation
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill requires connecting to the Rube MCP server at https://rube.app/mcp and mandates calling RUBE_SEARCH_TOOLS at runtime to fetch tool schemas and recommended execution plans that directly govern the agent's actions, so the external MCP endpoint (https://rube.app/mcp) is a runtime dependency that can control prompts/execution.
Audit Metadata