elorus-automation

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 Rube MCP endpoint (https://rube.app/mcp) to fetch live tool schemas and recommended execution plans that the agent must read and use to choose tool_slugs/arguments, so those third-party tool definitions could contain instructions that materially influence agent behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires adding and using the MCP server at https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS), which returns tool schemas and recommended execution plans that directly control the agent's instructions and execution, so this external endpoint is a runtime dependency that can control prompts/behavior.