pilvio-automation

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow calls RUBE_SEARCH_TOOLS against the connected Rube MCP server, and that tool-discovery response (tool schemas / recommended plans) is outsider-authored content that the agent ingests into its LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires contacting the external MCP endpoint https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS) to fetch tool schemas and recommended execution plans that directly determine agent instructions and tool execution, so this external URL is a required runtime dependency that can control the agent.