nano-banana-by-acedatacloud
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill connects to an external Model Context Protocol (MCP) server hosted at
https://nanobanana.mcp.acedata.cloud/mcpto facilitate image generation and editing tools. This is the intended behavior for the skill's functionality. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text for image generation, creating a surface for indirect prompt injection where instructions could be embedded in the processed data.
- Ingestion points: User-supplied prompts and media references are ingested by the
nanobanana_generate_imageandnanobanana_edit_imagetools. - Boundary markers: The
SKILL.mdfile requires the agent to confirm pricing and parameters with the user before executing tools, providing a manual oversight step. - Capability inventory: The skill possesses capabilities for network-based image generation, image editing, and status polling.
- Sanitization: The instructions specify that the agent must use original task IDs for polling and strictly report upstream errors and completion states without inventing information.
Audit Metadata