Pull a Docker image
AI agents invoke docker_pull_image to trigger actions in Cargoshipper. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Pulling a Docker image is not purely a read operation; it executes a network fetch and writes image layers to the local Docker daemon. It could be misused to pull malicious images, but it does not directly delete data or move money, making Execute the best fit with medium severity.
From the tool's definition 'Pull a Docker image' — downloading and installing a Docker image triggers an external network operation and modifies local Docker state (image cache)
Attacks that exploit this kind of access
Pull a Docker image. It is categorised as a Execute tool in the Cargoshipper MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cargoshipper MCP server in PolicyLayer and add a rule for docker_pull_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 Cargoshipper. Nothing to install.
docker_pull_image is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the docker_pull_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 docker_pull_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.
docker_pull_image is provided by the Cargoshipper MCP server (scarr7981/cargoshipper-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 →