stitch-mcp

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill shows and instructs embedding API keys directly in CLI commands and JSON (e.g., --header "X-Goog-Api-Key: your-api-key", config headers, and inline STITCH_API_KEY usage), which requires the LLM or agent to handle and potentially emit secret values verbatim, creating an exfiltration risk.

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow described in SKILL.md uses the Stitch MCP tool generate_screen_from_text/edit_screens, where the outsider’s free-form text is directly provided as the prompt (and designMd) argument to Stitch generation without any step of selecting a trusted predefined item first.