imagegen
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs its stated purpose of AI-based image generation and editing without any detected malicious patterns.
- [COMMAND_EXECUTION]: The skill uses local Python scripts (
scripts/image_gen.pyandscripts/postprocess_image.py) to handle API calls and image processing. These scripts use standard libraries and do not invoke arbitrary shell commands or external processes unsafely. - [CREDENTIALS_UNSAFE]: No hardcoded credentials were found. The skill correctly instructs the agent to use environment variables (
LLM_API_KEY,LLM_API_ENDPOINT) for API access, which is a standard and safe practice. - [EXTERNAL_DOWNLOADS]: The skill requires standard, well-known Python packages (
openai,pillow) which are typically installed from official registries like PyPI. - [DATA_EXFILTRATION]: Network activity is restricted to the specified AI model API endpoint. There are no patterns suggesting data exfiltration of sensitive project files.
- [OBFUSCATION]: All code and instructions are provided in clear text. No hidden or encoded malicious payloads were detected.
Audit Metadata