revid-tweet-to-talking-head

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

• Third-party content exposure detected (low risk: 0.10). The workflow takes arbitrary post URLs or text chosen by the user and passes them to an external video rendering API.

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

• Direct money access detected (high risk: 0.70). The skill describes creating talking-head videos from social posts using the Revid API/MCP server. Line 120 mentions a failure mode for insufficient credits where the agent can call buy_credit_pack. However, purchasing credit packs through an API or tool call constitutes a direct financial operation (a purchase/charge), and no qualifying independent access control is documented for that action. Therefore, it falls under High severity.