image-generator
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides the described image generation functionality. It interacts with legitimate API endpoints from ModelScope, Google Gemini, and RunningHub and performs standard file operations to save generated images.
- [DATA_EXFILTRATION]: Network communication is restricted to authorized API endpoints for the supported services. There is no evidence of the skill accessing sensitive local files (e.g., SSH keys, credentials) or exfiltrating data to external servers.
- [CREDENTIALS_UNSAFE]: The skill follows secure practices by using a configuration file (
config.json) for API keys. It provides an example template and explicitly notes that the configuration file should be kept local and ignored by version control. No hardcoded credentials were found. - [COMMAND_EXECUTION]: The script uses Python's standard libraries for HTTP requests and image processing. It does not invoke the shell for arbitrary command execution or process user-supplied input in an unsafe manner.
Audit Metadata