AI agents use compress_local_image to create or update resources in Test 1 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Test 1 environment.
Compression modifies a file in place or creates a compressed version, which is a reversible write operation. It does not delete or destroy data permanently, does not execute arbitrary code, and does not involve financial transactions. The blast radius is minimal as it only affects a local image file that the operator has intentionally specified.
From the tool's definition Tool name 'compress_local_image' and description 'Compress a local image file' indicates modification of an existing local file through compression (a reversible transformation).
Attacks that exploit this kind of access
Compress a local image file. It is categorised as a Write tool in the Test 1 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Test 1 MCP server in PolicyLayer and add a rule for compress_local_image: 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 Test 1. Nothing to install.
compress_local_image 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 compress_local_image 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 compress_local_image. 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.
compress_local_image is provided by the Test 1 MCP server (zhendi/tinypng-mcp-server). 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 →