AI agents use skill_add_assets to create or update resources in ClaudeSkills MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ClaudeSkills MCP Server environment.
The 'add' operation creates or attaches new assets to skills, modifying stored data reversibly. This is a Write action—data is created/added but can typically be removed or replaced. It is not Execute (no command execution), not Destructive (assets can be removed), and not Financial.
From the tool's definition Tool name 'skill_add_asset' (Add-verb) indicates creation or modification of assets. The description is empty, which limits certainty, but the verb 'add' combined with context from sibling tools (skill_read_asset, skill_list_assets) suggests this tool creates…
Documented attack patterns abuse exactly the kind of access skill_add_assets gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ClaudeSkills MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for skill_add_assets:
{
"version": "1",
"default": "deny",
"tools": {
"skill_add_assets": {
"limits": [
{
"counter": "skill_add_assets_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}skill_add_assets 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.
skill_add_assets. It is categorised as a Write tool in the ClaudeSkills MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ClaudeSkills MCP Server MCP server in PolicyLayer and add a rule for skill_add_assets: 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 ClaudeSkills MCP Server. Nothing to install.
skill_add_assets 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 skill_add_assets 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 skill_add_assets. 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.
skill_add_assets is provided by the ClaudeSkills MCP Server MCP server (tsoernes/skills-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ClaudeSkills 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.
13 ClaudeSkills MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.