superskills_env
AI agents call superskills_env to retrieve information from Superskills without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Given the 'env' suffix and lack of destructive modifiers (delete, drop, purge) or financial keywords, this most likely retrieves environment state. The empty description lowers confidence slightly, but the read-oriented naming and presence of dedicated write/run tools on the server suggest this is a query operation with no side effects.
From the tool's definition Tool name 'superskills_env' suggests reading environment variables or configuration. No description provided; inferred from naming convention and context of sibling tools (list, read, write, run operations).
Attacks that exploit this kind of access
superskills_env. It is categorised as a Read tool in the Superskills MCP Server, which means it retrieves data without modifying state.
Register the Superskills MCP server in PolicyLayer and add a rule for superskills_env: 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 Superskills. Nothing to install.
superskills_env 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 superskills_env 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 superskills_env. 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.
superskills_env is provided by the Superskills MCP server (lee2026-dev/superskills-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 →