beeminder-automation

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly requires calling the external MCP server (https://rube.app/mcp) via RUBE_SEARCH_TOOLS to ingest tool schemas and "recommended execution plans" which the agent must read and use to construct RUBE_MULTI_EXECUTE_TOOL calls, so untrusted third‑party responses could materially influence actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill requires contacting the MCP endpoint https://rube.app/mcp at runtime to fetch tool schemas and recommended execution plans that directly determine prompts/arguments and tool executions, making this a required external dependency that controls agent behavior.