codex-router-media
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local CLI tool (
mediaormodel-router.ps1) via the shell. This is the primary mechanism for the skill's functionality, used to process media generation requests. - [DATA_EXPOSURE]: The skill accesses a local manifest file (
~/.codex/codex-router/install-manifest.json) to determine the installation path of the tool. This is a standard operational procedure for locating the CLI binary within the specific environment. - [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided text as prompts for media generation. While this represents a data ingestion surface, the skill is limited to media output and contains explicit rules (Rule 4) to prevent the exfiltration of credentials or environment data, reducing the risk of exploitation.
Audit Metadata