codex
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to interact with the 'OpenAI Codex CLI', which involves executing shell commands to delegate tasks and query models.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8).
- Ingestion points: The skill gathers 'prompt context' and reads external reference files ('references/shared-procedure.md', 'references/cli-codex.md') to formulate requests.
- Boundary markers: There are no instructions to use delimiters or ignore instructions within the gathered context.
- Capability inventory: The skill has the ability to execute commands and present results based on the processed data.
- Sanitization: The instructions do not specify any validation or sanitization of the input data before it is passed to the CLI tool.
Audit Metadata