benchmark-email-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 contacting the Rube MCP server (https://rube.app/mcp) at runtime—RUBE_SEARCH_TOOLS returns tool slugs, schemas and recommended execution plans that directly control the agent's prompts/invocations and the skill mandates using that endpoint.
Audit Metadata