codex-computer-use
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for using shell commands like
codex exec,mdls, andopento interact with macOS and automate applications. These commands are necessary for the skill's documented purpose of bridging GUI operations to other agents. - [EXTERNAL_DOWNLOADS]: The documentation includes a standard installation command using
npxto fetch the skill from the author's public repository. This is a common and transparent installation pattern for this ecosystem. - [NO_CODE]: The skill contains no standalone executable scripts (e.g., .py or .js files), reducing the attack surface to the instructions provided in the markdown file.
- [SAFE]: The skill demonstrates security consciousness by including 'Safe Prompt Rules' that explicitly advise on using sandboxing flags (
--sandbox read-only), setting tool boundaries, and avoiding the exfiltration of sensitive UI data.
Audit Metadata