Execute an arbitrary SKILL expression in the Virtuoso environment.
AI agents invoke virtuoso_execute_skill to trigger actions in Virtuoso Schematic MCP. 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 directly executes arbitrary code in a live Virtuoso environment, which can trigger external operations, modify design state, query databases, or execute shell commands depending on what SKILL expressions are passed to it.
From the tool's definition "Execute an arbitrary SKILL expression in the Virtuoso environment" — the tool explicitly allows execution of arbitrary code (SKILL is Cadence's programming language for Virtuoso) with no restrictions on what expressions can be run.
Attacks that exploit this kind of access
Execute an arbitrary SKILL expression in the Virtuoso environment. It is categorised as a Execute tool in the Virtuoso Schematic MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Virtuoso Schematic MCP server in PolicyLayer and add a rule for virtuoso_execute_skill: 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 Virtuoso Schematic MCP. Nothing to install.
virtuoso_execute_skill 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 virtuoso_execute_skill 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 virtuoso_execute_skill. 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.
virtuoso_execute_skill is provided by the Virtuoso Schematic MCP server (michelebergo/virtuoso-schematic-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 →