talking-avatar-video

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

• Third-party content exposure detected (low risk: 0.10). The skill reads https://beatra.ai/skills/talking-avatar-video/sources.json to check for version updates, which represents fetched documentation/metadata rather than unselected outsider submission.

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

• Direct money access detected (high risk: 0.70). The skill operates a paid hosting service (Beatra) using prepaid credits and a stored OAuth bearer token with wallet:spend scope, which executes direct financial charges/purchases via tool calls. It relies entirely on client-side instruction prompts and user approvals rather than an independent execution-layer access control on the payment route itself.