Save an image to the appropriate project location with smart naming. Automatically detects project type (Next.js, React, Vue, Unity, Godot, etc.), finds the best directory for images, and applies the project
AI agents use save_asset to create or update resources in Nanobanana Pro — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nanobanana Pro environment.
This tool creates or modifies image files in project directories. While reversible (files can be deleted or overwritten), it alters the project filesystem. The automatic directory detection and naming mean the AI agent has limited control over exact placement but still performs a write operation. Not Destructive since file creation/modification is reversible.
From the tool's definition Tool 'saves' an image to 'project location' and 'automatically detects project type' and 'finds the best directory' — these are write operations that create/modify files on disk. Description truncated but indicates reversible file creation.
Attacks that exploit this kind of access
Save an image to the appropriate project location with smart naming. Automatically detects project type (Next.js, React, Vue, Unity, Godot, etc.), finds the best directory for images, and applies the project. It is categorised as a Write tool in the Nanobanana Pro MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nanobanana Pro MCP server in PolicyLayer and add a rule for save_asset: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Nanobanana Pro. Nothing to install.
save_asset is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the save_asset rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for save_asset. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
save_asset is provided by the Nanobanana Pro MCP server (rzgrozt/nanobanana-pro-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →