async-interview-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: 0.90). The skill explicitly requires adding and using the MCP endpoint https://rube.app/mcp at runtime and invokes RUBE_SEARCH_TOOLS / RUBE_MULTI_EXECUTE_TOOL to discover and execute remote tools, meaning that content from that URL can directly control prompts/execution of code.
Audit Metadata