openai-codex-security
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted codebase content. \n
- Ingestion points: The
scancommand and SDK functions inSKILL.mdread the contents of the local directory for analysis. \n - Boundary markers: Absent; the instructions do not specify any delimiters or safety markers to separate the scanned code from the agent's core logic. \n
- Capability inventory: The skill can read local files, execute CLI commands, and includes examples of automated fix workflows using
child_process.exec. \n - Sanitization: Absent; the skill does not describe any methods for filtering or escaping content found in the scanned files. \n- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the
@openai/codex-securitypackage from the NPM registry. This package resides within a trusted organization's namespace. \n- [COMMAND_EXECUTION]: The skill utilizes command-line tools such asnpmandnpxto manage dependencies and execute the security scanning CLI.
Audit Metadata