creativeclaw-nano-banana-pro
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied image URLs and text briefs to generate complex image prompts. Ingestion occurs via the
image_urlandextras.image_urlsparameters inSKILL.md. The skill uses a structured reference manifest and labeled sections as boundary markers to organize this data. It possesses the capability to interact with thecreative-clawMCP tool for image processing. No specific sanitization or filtering logic is described for the external inputs. - [EXTERNAL_DOWNLOADS]: The skill references the Creative Claw MCP tool at
https://app.creativeclaw.co/mcp/chatgptfor media and asset management.
Audit Metadata