The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the Codex CLI and relevant plugins from OpenAI's official GitHub and NPM repositories. These represent well-known and reputable sources for developer tools.
[COMMAND_EXECUTION]: The skill operates by executing shell commands via the codex CLI (e.g., codex review, codex rescue, codex login) to perform code analysis and task delegation. This is the primary intended function of the skill.
[INDIRECT_PROMPT_INJECTION]: The skill acts as a bridge, ingesting user-provided text and passing it directly to the Codex CLI for processing. This creates a potential surface for indirect injection if inputs are not properly sanitized.
Ingestion points: The skill accepts arbitrary text as arguments for commands like /codex:rescue <task> and /codex:adversarial-review <focus text>. These ingestion points are located in the command handlers described in SKILL.md.
Boundary markers: No specific delimiters or boundary markers are defined in the instructions to separate user input from system-level instructions passed to the CLI.
Capability inventory: The skill possesses the capability to execute shell commands via the codex CLI and provides documentation examples for using execSync to run these tasks.
Sanitization: Sanitization of user input is not explicitly described in the skill's markdown instructions; security relies on the input handling of the underlying Codex CLI tool.

codex-plugin-claude-code