posthog-automation

Warn

Audited by Snyk on Feb 27, 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 adding and calling the MCP endpoint https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS) to fetch current tool schemas that determine available tools/behavior, so external content from that URL can directly shape agent instructions and is a required runtime dependency.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 09:33 AM