bananahub
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes local Python scripts to handle image generation and provider configuration. These scripts are part of the skill's core functionality.
- [EXTERNAL_DOWNLOADS]: The skill connects to authorized image generation APIs and includes a telemetry feature for tracking template adoption. This telemetry communicates with the vendor's own infrastructure and respects user-defined privacy settings.
- [PROMPT_INJECTION]: The skill includes a comprehensive optimization pipeline designed to sanitize and structure user inputs. This provides a layer of defense against indirect prompt injection by extracting hard constraints and cleaning up keyword-heavy inputs.
Audit Metadata