beeminder-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 adding and calling the Rube MCP endpoint (https://rube.app/mcp) at runtime via RUBE_SEARCH_TOOLS / RUBE_MULTI_EXECUTE_TOOL to fetch tool schemas and trigger remote tool execution, which directly controls agent behavior and can execute remote code.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:29 AM