design-system-generator

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

• Third-party content exposure detected (low risk: 0.10). The required workflow uses WebFetch and shell commands (curl) to fetch and inspect arbitrary client website URLs provided by the user.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to execute a curl command against an arbitrary user-supplied URL during runtime, representing an inbound operational dependency on external dynamic content.