close-automation
Warn
Audited by Snyk on Mar 5, 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 connecting to and calling the Rube MCP endpoint (https://rube.app/mcp) at runtime—RUBE_SEARCH_TOOLS fetches tool schemas from that URL which directly determine the agent's available tools/instructions, and the skill depends on that external content.
Audit Metadata