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_url and extras.image_urls parameters in SKILL.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 the creative-claw MCP 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/chatgpt for media and asset management.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 12:38 PM
Security Audit — agent-trust-hub — creativeclaw-nano-banana-pro