AI agents call codex_skill_list to retrieve information from Codex without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a passive directory scan to enumerate skills from metadata files. It retrieves information without creating, modifying, deleting, or executing code. The blast radius of misuse is minimal—worst case an attacker gains visibility into available skills. No irreversible operations, code execution, or financial impact possible.
From the tool's definition Tool name is 'codex_skill_list' and description states it 'List[s] available Codex skills by scanning a directory for SKILL.md files.' The verb 'list' and action of scanning/querying a directory are read-only operations with no data modification or side…
Attacks that exploit this kind of access
List available Codex skills by scanning a directory for SKILL.md files. It is categorised as a Read tool in the Codex MCP Server, which means it retrieves data without modifying state.
Register the Codex MCP server in PolicyLayer and add a rule for codex_skill_list: 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 Codex. Nothing to install.
codex_skill_list 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 codex_skill_list 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 codex_skill_list. 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.
codex_skill_list is provided by the Codex MCP server (pigowenhsiao/codex-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
codex_skill_list is one line of Codex'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 →