u301-automation

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs the agent to call external Rube MCP endpoints (e.g., RUBE_SEARCH_TOOLS / RUBE_GET_TOOL_SCHEMAS against https://rube.app/mcp) and to read returned tool slugs, schemas, and recommended execution plans as part of its workflow, which exposes it to untrusted third‑party content that can materially influence actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires the external MCP endpoint https://rube.app/mcp at runtime and explicitly uses RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS / RUBE_MULTI_EXECUTE_TOOL to discover and invoke remote tools, meaning the external server can execute code and directly control agent actions.