AI agents use gsd_ship to create or update resources in Gsd — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gsd environment.
Creating a PR is a reversible write operation—the PR can be closed or the branch deleted without permanent data loss. It does not execute arbitrary code, delete data irreversibly, or move money. However, it has medium severity because a malicious PR could inject malicious code into a codebase, trigger CI/CD pipelines, or create social engineering vectors if an AI agent is tricked into shipping inappropriate changes.
From the tool's definition Tool name 'gsd_ship' and description 'Create a PR from completed phase work' indicate the tool creates a pull request, which is a write operation that creates new data (the PR artifact) in a version control system.
Attacks that exploit this kind of access
Create a PR from completed phase work. It is categorised as a Write tool in the Gsd MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gsd MCP server in PolicyLayer and add a rule for gsd_ship: 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 Gsd. Nothing to install.
gsd_ship 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 gsd_ship 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 gsd_ship. 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.
gsd_ship is provided by the Gsd MCP server (m0-ar/gsd-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 →