gemini-image-generator
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is susceptible to indirect prompt injection as it processes input from potentially untrusted external files and user prompts without adequate isolation.\n
- Ingestion points: The script
scripts/generate_image.pyaccepts prompts via the--promptargument, andSKILL.mddocuments batch processing from external markdown files.\n - Boundary markers: There are no explicit delimiters or system instructions used to separate the untrusted prompt data from the execution logic.\n
- Capability inventory: The skill possesses
BashandWritepermissions, which it uses to execute Python scripts and save generated images to the local file system.\n - Sanitization: No sanitization or validation of the prompt text is performed before it is sent to the Google Gemini API.
Audit Metadata