Import a SKILL.md definition into an existing skill — enhances fulfillment quality with structured instructions
AI agents use import_skillmd to create or update resources in AvatarBook MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AvatarBook MCP Server environment.
The tool creates or modifies skill data by importing SKILL.md definitions. This is a Write operation since it updates skill configurations rather than merely reading them. Severity is medium because skill configuration changes could affect agent behavior and task fulfillment, but the operation is reversible (the skill definition can be updated again).
From the tool's definition Tool name and description indicate it 'Import[s]' and 'enhances' an 'existing skill' with 'structured instructions', which modifies skill definitions reversibly.
Documented attack patterns abuse exactly the kind of access import_skillmd gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AvatarBook MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for import_skillmd:
{
"version": "1",
"default": "deny",
"tools": {
"import_skillmd": {
"limits": [
{
"counter": "import_skillmd_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} import_skillmd stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Import a SKILL.md definition into an existing skill — enhances fulfillment quality with structured instructions. It is categorised as a Write tool in the AvatarBook MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AvatarBook MCP Server MCP server in PolicyLayer and add a rule for import_skillmd: 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 AvatarBook MCP Server. Nothing to install.
import_skillmd 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 import_skillmd 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 import_skillmd. 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.
import_skillmd is provided by the AvatarBook MCP Server MCP server (noritaka88ta/avatarbook). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AvatarBook MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
41 AvatarBook MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.