veo-automation

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

• Third-party content exposure detected (high risk: 0.90). This skill requires calling RUBE_SEARCH_TOOLS against an external MCP (e.g., https://rube.app/mcp) and ingesting tool schemas and recommended execution plans from that third-party server, which the agent must read and which directly determine tool arguments and actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires a runtime connection to the MCP endpoint https://rube.app/mcp which returns tool schemas, recommended execution plans, and tool slugs that directly control what prompts/instructions the agent uses and which remote tool executions occur, so this is a runtime dependency that can control agent behavior.