AI agents call skills_get_options 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 retrieve or list available options (likely for a skills registry), which is a read-only operation. The 'get_' naming convention and the absence of any indication of modification, execution, or deletion suggests low severity. Confidence is moderate (0.6) because the empty description provides no explicit confirmation of its function.
From the tool's definition Tool name 'skills_get_options' suggests retrieval of configuration or metadata options. The empty description limits certainty, but the 'get' prefix and parallel context with other tools like 'skills_get_asset', 'skills_get_body', and 'skills_get_reference'…
Attacks that exploit this kind of access
skills_get_options. 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_get_options: 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_get_options 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_get_options 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_get_options. 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_get_options 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 →