tiktok-campaign-setup

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow reads outsider-authored free text from TikTok Spark creative assets/organic post content (e.g., via tiktok_ads_upload_video_from_url / raw /ad/create objects using tiktok_item_id), so attacker-published captions/comments/metadata associated with those posts can be ingested indirectly at ad creation time.

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

• Direct money access detected (high risk: 1.00). The skill explicitly includes API calls that create and manage TikTok ad campaigns/ad groups with budget parameters (e.g., tiktok_ads_create_campaign with budget, tiktok_ads_create_adgroup with budget) and instructions to scale/pause budgets post-launch. These are specific ad-spend management actions (setting/updating budgets and pausing campaigns), which constitute direct financial execution authority for ad spend.