modify_script
AI agents use modify_script to create or update resources in GameDevBench MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GameDevBench MCP environment.
modify_script creates or alters script files, which is reversible (Write category) but has high severity because malicious script modifications in a game engine context could alter game behavior, introduce vulnerabilities, or compromise the development environment. Confidence is slightly reduced due to the empty description, but the tool name and sibling context make the classification clear.
From the tool's definition Tool name 'modify_script' indicates modification of scripts. The description is empty, providing no details about scope or safeguards.
Attacks that exploit this kind of access
modify_script. It is categorised as a Write tool in the GameDevBench MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GameDevBench MCP server in PolicyLayer and add a rule for modify_script: 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 GameDevBench MCP. Nothing to install.
modify_script 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 modify_script 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 modify_script. 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.
modify_script is provided by the GameDevBench MCP server (seeleai/gamedevbench-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 →