wati-automation

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly requires calling RUBE_SEARCH_TOOLS / RUBE_GET_TOOL_SCHEMAS (against the external MCP endpoint https://rube.app/mcp) to ingest externally-provided tool schemas and recommended execution plans that the agent must read and act on, which are untrusted third-party inputs that can influence subsequent tool use.

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 using the MCP server https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS / RUBE_MANAGE_CONNECTIONS) to fetch tool schemas and recommended execution plans which directly control the agent's prompts/execution flow, so this external endpoint is a runtime dependency that can control instructions.