formation-designer
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill content is purely instructional and serves as a reference for configuring agent-model relationships. It does not contain executable scripts or instructions to perform dangerous operations.
- [SAFE]: External URL references point to GitHub repositories for JSON schema validation and matching guides, which is standard practice for configuration management.
- [SAFE]: The skill mentions local configuration paths (e.g.,
~/.config/opencode/prompts/*.append.md) solely for the purpose of defining where the agent should look for additional prompt context, which is a benign configuration directive. - [SAFE]: No obfuscation, data exfiltration patterns, or unauthorized privilege escalation commands were found.
Audit Metadata