imagegen
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a 'built-in first' policy, preferring platform-native tools over external scripts. It requires explicit user confirmation before switching to the CLI fallback mode that uses external APIs.
- [COMMAND_EXECUTION]: For its fallback mode, the skill utilizes a local script (
scripts/image_gen.py) to interface with image generation models. This execution is gated by user approval and intended for the skill's primary purpose. - [EXTERNAL_DOWNLOADS]: The skill manages its requirements using standard package managers to install well-known, trusted libraries (
openai,pillow) from official registries. - [CREDENTIALS_SAFE]: The skill provides secure guidance for handling sensitive information. It instructs users to set the
OPENAI_API_KEYas a local environment variable and explicitly warns against pasting keys directly into the chat. - [DATA_EXPOSURE]: Files and generated assets are stored in designated project directories (
output/imagegen/) or platform-managed paths ($CODEX_HOME), following standard workspace practices.
Audit Metadata