waboxapp-automation

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill requires calling RUBE_SEARCH_TOOLS against the external Rube MCP (e.g., https://rube.app/mcp) to fetch live tool slugs, schemas, and recommended execution plans (see "Tool Discovery" / "Core Workflow Pattern" in SKILL.md), which the agent is expected to read and act on—exposing it to untrusted third-party content that could inject instructions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill requires connecting at runtime to the MCP server at https://rube.app/mcp, which provides tool schemas and recommended execution plans that directly determine what the agent will instruct and execute, so this external endpoint can control prompts/execution.