tisane-automation

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

• Third-party content exposure detected (high risk: 0.70). The skill instructs the agent to call RUBE_SEARCH_TOOLS against the external Rube MCP endpoint (https://rube.app/mcp) and to read returned tool slugs, input schemas and recommended execution plans, which are third-party content the agent must interpret and could contain untrusted or user-provided instructions.