muapi-url-to-design

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

• Third-party content exposure detected (low risk: 0.10). The workflow takes an arbitrary user-supplied website URL and passes it into a generation prompt for image models without reading or ingesting external web page text into the LLM context.

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

• Potentially malicious external URL detected (high risk: 0.70). An operational dependency on https://api.muapi.ai/api/v1 is evidenced via direct curl fallback usage in the execution instructions, but the publisher provenance is unknown and untrusted, resulting in a high tier.