postmark-automation
Warn
Audited by Snyk on Feb 20, 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 server at https://rube.app/mcp (via RUBE_SEARCH_TOOLS) to fetch current tool schemas, meaning remote content from that URL is fetched at runtime and can directly control the agent's prompts and available tool execution.
Audit Metadata