openai-docs

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill declares and at-runtime uses the MCP tool at https://developers.openai.com/mcp (also referenced in the install command codex mcp add openaiDeveloperDocs --url https://developers.openai.com/mcp) to fetch OpenAI docs which are then directly used to shape agent prompts/responses, so this external URL is a runtime dependency that controls agent behavior.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The prompt explicitly directs installing an MCP server and to retry the install with escalated permissions to bypass sandboxing (without asking the user), which requires privilege escalation and modifies the system state.