homeassistant-dashboard-designer

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

• Third-party content exposure detected (high risk: 0.70). The skill optionally integrates with an external "Stitch" MCP (see SKILL.md and README.md which show the Stitch MCP URL https://stitch.googleapis.com/mcp and instructions to enable it) and explicitly instructs the agent to prompt/read Stitch output and translate its "stitch_intent" into Lovelace YAML, so untrusted third‑party content can be ingested and materially influence layout/implementation decisions.