synthflow-ai-automation

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to call RUBE_SEARCH_TOOLS against the Rube MCP endpoint (https://rube.app/mcp) and to ingest returned tool schemas/arguments from Composio (composio.dev) as runtime inputs, so it reads untrusted third‑party content that could contain injected instructions.