AI agents call diff_files to retrieve information from PSKit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The diff operation is a read-only query that compares two files and returns their differences. It has no side effects on the filesystem or any data. Even in the context of a PowerShell automation server, diff is fundamentally a retrieval operation. The 5-tier safety pipeline mentioned in the server description further suggests controls are in place.
From the tool's definition Tool name is 'diff_files' and description states 'Show a unified diff between two files' — this retrieves and displays differences between files without modifying, creating, or deleting data.
Attacks that exploit this kind of access
Show a unified diff between two files. It is categorised as a Read tool in the PSKit MCP Server, which means it retrieves data without modifying state.
Register the PSKit MCP server in PolicyLayer and add a rule for diff_files: 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 PSKit. Nothing to install.
diff_files is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the diff_files 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 diff_files. 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.
diff_files is provided by the PSKit MCP server (nickalus12/pskit). 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 →