modelry-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 explicitly requires contacting the Rube MCP server at https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS / RUBE_MULTI_EXECUTE_TOOL), which returns tool schemas and execution plans that directly control agent prompts and trigger remote tool execution, so this endpoint is a runtime dependency that can control/execute behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:01 PM