model-profile-resolution
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill manages model selection logic based on predefined profiles. It reads the active profile from
.planning/config.jsonand maps specific agent roles to appropriate AI models (e.g., mapping 'gsd-executor' to 'claude-sonnet-4' in the 'balanced' profile). All analyzed behaviors, including cost estimation and profile switching, are consistent with its stated purpose. No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected.
Audit Metadata