gpt-image

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

• Third-party content exposure detected (low risk: 0.10). The workflow references a GitHub repository containing documentation at https://github.com/AceDataCloud/Skills/tree/main/skills/gpt-image-2-5, which falls under low risk as an active search/fetch of documentation.

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

• Direct money access detected (medium risk: 0.30). The skill uses paid image generation tools (gpt_image_generate, gpt_image_edit) that draw from Ace Credits. This constitutes a direct financial operation (purchases/charges). Access is controlled via an authenticated API token (ACEDATACLOUD_API_TOKEN) passed to the MCP server, satisfying the independent access control requirement.