codex-cli-rules
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill contains instructional bash snippets for using the
codex execCLI tool. These examples demonstrate standard programmatic interactions, such as piping input from stdin and capturing output/logs to local temporary files. No unauthorized or dangerous command patterns were identified. - [DATA_EXFILTRATION]: No exfiltration patterns detected. The scripts use
/tmp/for temporary data storage and do not perform network operations to untrusted domains or access sensitive system configuration files. - [PROMPT_INJECTION]: The skill body consists of technical documentation and usage rules. It does not contain instructions that attempt to override agent behavior, bypass safety filters, or extract system prompts.
Audit Metadata