social-talking-head-video

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

• Third-party content exposure detected (low risk: 0.10). The workflow reads arbitrary web pages specified by the user or found via research for B-roll generation, presenting a low-risk indirect prompt injection exposure via rollberry capture or browser capture.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references an external GitHub repository (https://github.com/co-r-e/rollberry) via npx to capture browser B-roll at runtime, representing an unofficial operational dependency.