typefully-automation

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to call an external MCP server (https://rube.app/mcp) via RUBE_SEARCH_TOOLS to fetch tool schemas and "recommended execution plans" that the agent must read and use to determine which tools/arguments to execute, so untrusted third-party content from that endpoint 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 connecting to the Rube MCP server at https://rube.app/mcp at runtime to fetch tool schemas and recommended execution plans (via RUBE_SEARCH_TOOLS / RUBE_MULTI_EXECUTE_TOOL), which directly control the agent's prompts/execution flow, so this external endpoint is a runtime dependency that influences behavior.