aura-asset-images

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

• Third-party content exposure detected (low risk: 0.10). The required workflow directs the agent to search and retrieve images from aura.build/assets using arbitrary tags, which is an external search/fetch flow exposing the agent to low indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill references stock images hosted on a third-party Supabase storage bucket (hoirqrkdgbmvpwutwuwj.supabase.co), which serves as an arbitrary, unauthenticated, and uncontrolled external dependency without first-party vendor provenance.