AI agents invoke gradle-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.
This tool executes build processes which can run arbitrary code on the system. The blast radius is high because gradle builds can execute shell commands, download dependencies, and run custom tasks defined in build files. Misuse could lead to code execution, unauthorized package installation, or system compromise.
From the tool's definition Tool name 'gradle-build' with description 'Runs' indicates execution of build operations. Gradle is a build automation tool that executes arbitrary code during builds, including custom tasks, plugins, and scripts.
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 gradle-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.
gradle-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 gradle-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 gradle-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.
gradle-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.