models-config

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

• Third-party content exposure detected (low risk: 0.10). The skill fetches JSON data from models.dev during price updates, but this public registry content requires explicit user invocation and is classified as low risk.

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

• Potentially malicious external URL detected (medium risk: 0.30). The script fetches pricing data at runtime from https://models.dev/api.json to update local model configuration, representing an inbound operational dependency on a third-party service.