AI agents use generate_skills to create or update resources in Loreto — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Loreto environment.
Generates new skills (creates data structures/artifacts) that are stored and reusable, making it a Write operation. Severity is medium because skill generation could create unintended or malicious code artifacts, though effects are reversible (skills can be deleted). Confidence is 0.75 rather than higher due to empty tool description, which limits direct evidence, but server context strongly indicates skill creation.
From the tool's definition Tool name 'generate_skills' and server purpose indicate creation of reusable Claude Code skills from various media.
Documented attack patterns abuse exactly the kind of access generate_skills gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Loreto, and nothing reaches the server without passing your rules. This is the rule we recommend for generate_skills:
{
"version": "1",
"default": "deny",
"tools": {
"generate_skills": {
"limits": [
{
"counter": "generate_skills_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}generate_skills 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.
generate_skills. It is categorised as a Write tool in the Loreto MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Loreto MCP server in PolicyLayer and add a rule for generate_skills: 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 Loreto. Nothing to install.
generate_skills 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 generate_skills 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 generate_skills. 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.
generate_skills is provided by the Loreto MCP server (kopias/loreto-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Loreto, 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.
13 Loreto tools catalogued and risk-classified — across an index of 43,000+ MCP servers.