godial-automation

Warn

Audited by Snyk on Feb 17, 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 instructs the agent to call external MCP endpoints (e.g., https://rube.app/mcp and Composio tool discovery via RUBE_SEARCH_TOOLS / RUBE_GET_TOOL_SCHEMAS) to fetch tool schemas, execution plans, and other metadata, meaning the agent will ingest and act on untrusted third-party content from public services.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 1.00). The skill requires a runtime connection to the external MCP endpoint https://rube.app/mcp to discover and invoke remote tools (RUBE_SEARCH_TOOLS / RUBE_MULTI_EXECUTE_TOOL), which executes remote tool code and therefore directly controls agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 12:24 AM