renderform-automation

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to call RUBE_SEARCH_TOOLS against the Rube MCP endpoint (e.g., add https://rube.app/mcp) to fetch tool schemas and recommended execution plans, which are untrusted third-party responses that the agent must read and use to decide which tools and arguments to execute, allowing indirect instructions to influence 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 contacting the MCP endpoint https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS), which returns tool schemas and recommended execution plans that directly influence agent instructions and are a required dependency.