pi-custom-model
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill follows best practices by instructing the agent to avoid displaying secrets.
- [COMMAND_EXECUTION]: The skill requires executing local 'pi' CLI commands to verify versions and model lists as part of the configuration workflow.
- [INDIRECT_PROMPT_INJECTION]: The skill processes local JSON configuration files, representing a potential but unexploited attack surface common to configuration tools.
Audit Metadata