AGENT LAB: SKILLS

sendgrid-automation

Warn

Audited by Snyk on Feb 15, 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 adding and calling the runtime MCP endpoint https://rube.app/mcp (via RUBE_SEARCH_TOOLS/RUBE_MANAGE_CONNECTIONS) to retrieve tool schemas that directly control agent instructions, so this URL is a required runtime dependency that can alter prompts/behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:24 PM