higress-auto-router
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the execution of a local shell script named
./get-ai-gateway.shto perform its primary functions. - [COMMAND_EXECUTION]: User-supplied input from the request (e.g., trigger phrases or model names) is interpolated directly into shell command strings (e.g.,
./get-ai-gateway.sh route add --trigger "<trigger-phrases>"). This creates a vulnerability surface for command injection if the input contains shell metacharacters or if the script does not implement robust sanitization.
Audit Metadata