AI agents invoke maven-build to trigger actions in Github. 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.
Maven builds execute external processes and can run arbitrary code through build plugins, test suites, and custom build goals. While not destructive by itself, the execution of untrusted or attacker-controlled build configurations could compromise the system. This falls under Execute category due to command execution with effects dependent on build configuration arguments.
From the tool's definition Tool name 'maven-build' and description 'Runs' indicate execution of build operations. Maven build commands execute arbitrary code compilation, testing, and build processes defined in pom.xml files.
Attacks that exploit this kind of access
Runs. It is categorised as a Execute tool in the Github MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Github MCP server in PolicyLayer and add a rule for maven-build: 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 Github. Nothing to install.
maven-build 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 maven-build 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 maven-build. 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.
maven-build is provided by the Github MCP server (@paretools/github). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.