creativeclaw-seedream-5-pro
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill configuration defines a dependency on an MCP tool hosted at https://app.creativeclaw.co/mcp/chatgpt. This endpoint provides the necessary functions for media processing, asset management, and model interaction within the vendor's ecosystem.
- [DATA_EXFILTRATION]: The skill instructions describe workflows for uploading and importing media files to the Creative Claw platform. This includes using presigned URLs for direct uploads and importing files from the local environment or external URLs. These operations are essential to the skill's purpose and utilize vendor-controlled infrastructure.
- [COMMAND_EXECUTION]: The skill specifies the use of various tool calls, such as get_model_params, import_chatgpt_media, and merge_media, to manage the image generation pipeline and post-processing tasks. These commands are part of the authorized toolset provided by the vendor.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user data, including images containing annotations, sketches, or text used as spatial guidance for the generation model. This is an intended functional capability of the Seedream 5 Pro model as described in the documentation and does not represent a malicious pattern in the skill's logic.
Audit Metadata