dialpad-automation
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill requires calling RUBE_SEARCH_TOOLS against the public Rube MCP endpoint (https://rube.app/mcp) to retrieve tool slugs, input schemas and execution plans that the agent must read and act on, which are untrusted third‑party responses that could carry indirect prompt injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill instructs adding https://rube.app/mcp as the MCP server and then relies on runtime calls (RUBE_SEARCH_TOOLS, RUBE_MULTI_EXECUTE_TOOL) to fetch tool schemas and execute tools from that server, meaning remote content can directly control agent behavior and execution.
Audit Metadata