create-ai-avatar

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

• Third-party content exposure detected (low risk: 0.10). The script scripts/hear.mjs ingests arbitrary audio or video files via ElevenLabs Speech-to-Text API, but does not monitor outsider-authored feeds or communications directly without active user selection.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 0.70). The skill implements direct financial operations through API interactions with paid external services (HeyGen and ElevenLabs) to train digital twins, synthesize voices, and render videos, incurring real monetary costs (e.g., training and rendering charges mentioned in SKILL.md:29, SKILL.md:40, SKILL.md:42, SKILL.md:75, SKILL.md:78). However, there is no qualifying independent access control or authentication mechanism enforced by the service or execution layer described for these payment routes; the scripts merely read API keys from environment variables or local configuration files without independent service-side user authentication or transaction authorization gates.