gemini-image-coder
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted user data.
- Ingestion points: The skill accepts user-provided text through the
promptargument inscripts/generate_image.pyand theinstructionargument inscripts/edit_image.py. - Boundary markers: No delimiters or protective instructions are used to wrap user input before it is passed to the API call in
client.models.generate_content. - Capability inventory: The scripts have the ability to read and write files (images) and initiate network requests to Google API endpoints.
- Sanitization: The skill does not validate or sanitize the text prompts provided by the user.
Audit Metadata