Delete the layer mask from active layer
AI agents call photoshop_delete_layer_mask to permanently remove resources in Photoshop MCP Windows-First — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a layer mask is an irreversible destructive action — once removed, the mask and its pixel data are permanently lost unless the user manually undoes the action within Photoshop's limited undo history. The blast radius is medium as it affects only the layer mask of the active layer, not the entire document.
From the tool's definition Delete the layer mask from active layer
Attacks that exploit this kind of access
Delete the layer mask from active layer. It is categorised as a Destructive tool in the Photoshop MCP Windows-First MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Photoshop MCP Windows-First MCP server in PolicyLayer and add a rule for photoshop_delete_layer_mask: 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 Photoshop MCP Windows-First. Nothing to install.
photoshop_delete_layer_mask is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the photoshop_delete_layer_mask 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 photoshop_delete_layer_mask. 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.
photoshop_delete_layer_mask is provided by the Photoshop MCP Windows-First MCP server (rookietopred02-gif/photoshop-mcp-windows-first). 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 →