codex
Warn
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill constructs shell commands by piping user-provided prompts directly into a CLI (e.g.,
echo "your prompt here" | codex exec ...). This pattern is highly susceptible to command injection if the prompt contains shell metacharacters like backticks, semicolons, or command substitution syntax. - [COMMAND_EXECUTION]: The instructions mandate suppressing standard error output (
2>/dev/null) for all commands. This practice hides potential warnings, errors, or execution logs that might otherwise alert the user to unauthorized or suspicious system behavior. - [COMMAND_EXECUTION]: The skill provides access to high-privilege execution modes, such as
--sandbox danger-full-access, which may grant the CLI tool broad permissions including network and file system access.
Audit Metadata