AI agents call skills_list_all to retrieve information from Skills without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to enumerate or retrieve all available skills from the registry without modification. The 'list_all' pattern is characteristic of read operations. While the description is empty (lowering confidence slightly), the tool name and the read-only nature of sibling tools in the registry strongly indicate this is a query/retrieval function with no side effects.
From the tool's definition Tool name 'skills_list_all' indicates a listing/retrieval operation with no destructive or side-effect keywords.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
skills_list_all. It is categorised as a Read tool in the Skills MCP Server, which means it retrieves data without modifying state.
Register the Skills MCP server in PolicyLayer and add a rule for skills_list_all: 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 Skills. Nothing to install.
skills_list_all 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 skills_list_all 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 skills_list_all. 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.
skills_list_all is provided by the Skills MCP server (jignesh-ponamwar/skills-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 →