Return URLs to machine-readable documentation for AI agents integrating with Execution Market: skill.md (full reference), A2A agent card, REST OpenAPI, and the MCP server endpoint.
AI agents call em_get_skill_reference to retrieve information from Execution Market without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and provides reference documentation URLs for integration purposes. This is a read-only operation with no side effects, no data modification, and no capability to trigger external tasks or financial transactions. The low severity reflects that misuse cannot cause harm—an AI agent requesting documentation cannot abuse this to damage systems or funds.
From the tool's definition Tool returns URLs to documentation; explicitly described as 'Return URLs to machine-readable documentation' with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Return URLs to machine-readable documentation for AI agents integrating with Execution Market: skill.md (full reference), A2A agent card, REST OpenAPI, and the MCP server endpoint. It is categorised as a Read tool in the Execution Market MCP Server, which means it retrieves data without modifying state.
Register the Execution Market MCP server in PolicyLayer and add a rule for em_get_skill_reference: 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 Execution Market. Nothing to install.
em_get_skill_reference 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 em_get_skill_reference 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 em_get_skill_reference. 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.
em_get_skill_reference is provided by the Execution Market MCP server (https://mcp.execution.market/mcp/). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
em_get_skill_reference is one line of Execution Market's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →