domains
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a shell wrapper script scripts/koyeb-cli.sh to execute the koyeb binary with arbitrary arguments provided by the agent. This is the primary method for managing Koyeb resources.
- [COMMAND_EXECUTION]: Reference documentation in references/koyeb-cli.md provides examples of complex shell pipelines using awk and xargs to perform bulk administrative actions such as deleting all sandbox services.
- [CREDENTIALS_UNSAFE]: The skill provides instructions for authenticating with the Koyeb CLI using the KOYEB_API_TOKEN environment variable or the --token flag. It includes documentation for the --debug-full flag, noting that it will display sensitive information, which serves as a security warning for the user.
- [SAFE]: All operations described and enabled by the skill are within the expected administrative scope of the Koyeb platform. No malicious behaviors such as unauthorized data exfiltration or persistence mechanisms were detected.
Audit Metadata