create-design-md

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow explicitly instructs the agent to browse/read official or user-provided Design.md requirements from runtime URLs (e.g., https://stitch.withgoogle.com/...), which is public web content authored by outsiders that can be ingested as readable text into the LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent at runtime to browse and read the Google Stitch Design.md pages (https://stitch.withgoogle.com/docs/design-md/overview/ and https://stitch.withgoogle.com/docs/design-md/specification/), which would be fetched and used to directly control the agent's output/instructions for producing DESIGN.md.