opencode-agent-creator
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides comprehensive guidance and templates for creating OpenCode agents without introducing any malicious code or configurations.
- [SAFE]: No instances of prompt injection, data exfiltration, or obfuscation were found in the instructions or example prompts.
- [SAFE]: The skill encourages security best practices, such as restricting tool access and requiring user approval ('ask') for risky operations like file editing or shell command execution.
- [SAFE]: All external references target official documentation and standard schema URLs related to the OpenCode platform.
Audit Metadata