sensibo-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: 0.90). The skill requires contacting the Rube MCP endpoint (https://rube.app/mcp) at runtime to fetch tool schemas and recommended execution plans which directly determine tool slugs/arguments and thus control what remote actions/code the agent will execute.
Audit Metadata