AI agents call vibekit_get_skill to retrieve information from Vibekit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
vibekit_get_skill retrieves skill content by ID. This is purely a data retrieval operation with no modification, deletion, or execution capabilities. The read operation poses minimal risk unless the skill content itself contains sensitive information, but the tool itself performs no destructive or dangerous actions.
From the tool's definition Tool description states 'Fetch the full content of a specific skill', using the verb 'Fetch' which is a read operation with no side effects. The server description mentions 'monitor logs' and 'retrieves' as read activities.
Attacks that exploit this kind of access
Fetch the full content of a specific skill. Use vibekit_list_skills to discover available skill IDs. It is categorised as a Read tool in the Vibekit MCP Server, which means it retrieves data without modifying state.
Register the Vibekit MCP server in PolicyLayer and add a rule for vibekit_get_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 Vibekit. Nothing to install.
vibekit_get_skill 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 vibekit_get_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 vibekit_get_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.
vibekit_get_skill is provided by the Vibekit MCP server (vibekit-apps/vibekit-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 →