remove-bg-automation

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

• Third-party content exposure detected (high risk: 0.90). The skill requires calling RUBE_SEARCH_TOOLS against the external Rube MCP (https://rube.app/mcp) and ingesting returned tool schemas and recommended execution plans that the agent must interpret to choose tool_slugs and arguments, so untrusted third-party responses could alter the agent's 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 external MCP endpoint https://rube.app/mcp at runtime (used by RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS) and relies on the returned tool schemas and execution plans to determine and drive agent instructions, so the fetched content can directly control prompts/execution.