AI agents use skillsmp_install to create or update resources in Skillsmp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Skillsmp environment.
Installing a skill writes new data or configurations to a namespace (global, project, or sandbox). This is a reversible write operation (skills can be uninstalled/removed), not inherently destructive, financial, or code execution. Medium severity because installing to a global namespace could affect all users or projects on the system.
From the tool's definition 'Install a skill to specified namespace' — installs/creates a skill in a target namespace
Attacks that exploit this kind of access
Install a skill to specified namespace (global/project/sandbox). It is categorised as a Write tool in the Skillsmp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Skillsmp MCP server in PolicyLayer and add a rule for skillsmp_install: 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 Skillsmp. Nothing to install.
skillsmp_install 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 skillsmp_install 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 skillsmp_install. 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.
skillsmp_install is provided by the Skillsmp MCP server (@luckybalabalaya/skillsmp-mcp-server). 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 →